© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    the word "powerful" and sometimes the word "sport."

    oai_token-act-pair · gemini-2.0-flash

    strength

    np_max-act · gemini-2.0-flash

    powerful

    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
    Gambas
    -0.75
    enderror
    -0.71
    rungsseite
    -0.70
    endpush
    -0.68
     fratelli
    -0.60
     BoxFit
    -0.60
    oredCriteria
    -0.60
    TRIBUN
    -0.60
     GenerationType
    -0.60
     Introduce
    -0.60
    POSITIVE LOGITS
    gamesh
    0.72
     Jove
    0.65
    ạnh
    0.64
     Phry
    0.63
    $.
    0.63
     ་་
    0.63
    .",
    0.63
    ihnachten
    0.62
     Diſ
    0.61
     itſelf
    0.60
    Activations Density 2.319%

    No Known Activations