© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    references to people with last names that happen to also be common first names

    oai_token-act-pair · gemini-2.0-flash

    Thomas or Smith

    np_max-act · gemini-2.0-flash

    Thomas

    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
     N
    -1.35
    <eos>
    -1.34
     T
    -1.33
     I
    -1.27
     B
    -1.26
     R
    -1.25
     L
    -1.24
     G
    -1.23
     P
    -1.23
     S
    -1.23
    POSITIVE LOGITS
     myſelf
    2.33
     itſelf
    2.30
     Efq
    2.13
     Monfieur
    2.11
     ―――――
    2.09
     Majefty
    2.09
     Theſe
    2.09
     raiſ
    2.03
     purpoſe
    2.02
     pleaſure
    2.00
    Activations Density 2.718%

    No Known Activations