© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10555
    Prev
    Next
    INDEX
    Explanations

    words related to business and customer service, but also words related to people's innate natures.

    oai_token-act-pair · gemini-2.0-flash

    requests and events

    np_max-act · gemini-2.0-flash

    say "a" words Method used: 2 — because most tokens after the trigger begin with "a"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yakarta
    -0.50
    ándor
    -0.48
     specific
    -0.45
     Doble
    -0.44
    ArgsConstructor
    -0.44
    ônio
    -0.44
    >-->
    -0.44
     inherent
    -0.43
    Commons
    -0.43
     inspired
    -0.43
    POSITIVE LOGITS
     whom
    0.85
     who
    0.84
    whom
    0.81
    who
    0.81
    ScopeManager
    0.81
     للاسماء
    0.81
    tvguidetime
    0.79
    Autoritní
    0.75
     siapa
    0.73
    Hvem
    0.73
    Activations Density 3.052%

    No Known Activations