© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12760
    Prev
    Next
    INDEX
    Explanations

    code related to web buttons

    oai_token-act-pair · gemini-2.0-flash

    button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ^(@)
    -0.87
    __':
    -0.85
     Wikimedijinoj
    -0.84
     Anſ
    -0.83
     ſhe
    -0.81
     purpoſe
    -0.79
     betweenstory
    -0.78
     Efq
    -0.78
     Reſ
    -0.78
     Houſe
    -0.77
    POSITIVE LOGITS
    </b>
    0.57
    sizeCache
    0.56
     “
    0.51
    </strong>
    0.50
    TS
    0.50
     "
    0.49
    <eos>
    0.48
    </i>
    0.48
    or
    0.48
     la
    0.46
    Activations Density 2.025%

    No Known Activations