© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10771
    Prev
    Next
    INDEX
    Explanations

    verbs or commands.

    oai_token-act-pair · gemini-2.0-flash

    Food sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     collect
    -0.65
    <bos>
    -0.62
     communicate
    -0.58
     deny
    -0.55
     protect
    -0.55
     stop
    -0.54
    collect
    -0.53
     utilize
    -0.53
     operate
    -0.53
     pay
    -0.52
    POSITIVE LOGITS
     resourceCulture
    0.93
     MainAxisSize
    0.83
     فريبيس
    0.83
    ReusableCell
    0.77
     Efq
    0.75
     vPvB
    0.74
    دانشنامهٔ
    0.74
    WithIOException
    0.73
    TagMode
    0.72
    parsedMessage
    0.70
    Activations Density 1.802%

    No Known Activations