© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15938
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to politics, history, or events.

    oai_token-act-pair · gemini-2.0-flash

    legal/controversial situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     BoxDecoration
    -0.87
    ValueStyle
    -0.85
    UnknownFieldSet
    -0.75
    ReusableCell
    -0.68
    الإنجليزية
    -0.67
    InvalidProtocol
    -0.66
    rxjs
    -0.64
    WriteBarrier
    -0.64
    rungsseite
    -0.63
     contextLoads
    -0.63
    POSITIVE LOGITS
    گرام
    0.46
    UrlResolution
    0.44
     taget
    0.42
    sender
    0.40
    jublj
    0.40
    řeba
    0.39
    Illustrated
    0.39
     SafeMath
    0.39
    setMode
    0.39
    自信
    0.39
    Activations Density 32.064%

    No Known Activations