© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9946
    Prev
    Next
    INDEX
    Explanations

    code from programming languages.

    oai_token-act-pair · gemini-2.0-flash

    Tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     fotografico
    -0.55
     refusé
    -0.52
    auen
    -0.51
    domada
    -0.50
     įsi
    -0.49
    upsi
    -0.48
    NameValuePair
    -0.48
     vaisselle
    -0.48
     iload
    -0.47
    ftime
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.71
    {}{}
    0.56
    èdia
    0.55
     Taktlose
    0.52
    ="#">
    0.52
     يتيمه
    0.52
     typelib
    0.52
     것이다
    0.51
    ftagPool
    0.49
     beginnetje
    0.48
    Activations Density 1.090%

    No Known Activations