© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12738
    Prev
    Next
    INDEX
    Explanations

    hedging language

    oai_token-act-pair · gemini-2.0-flash

    mentioning

    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
    kháu
    -0.60
    Vidite
    -0.55
    principalTable
    -0.52
     ویکی‌پدیای
    -0.51
    thâu
    -0.50
    erunner
    -0.49
    UnusedPrivate
    -0.47
    pania
    -0.47
     biel
    -0.47
    Referanser
    -0.47
    POSITIVE LOGITS
     jScrollPane
    0.64
     StatelessWidget
    0.63
     StatefulWidget
    0.59
     AttributeSet
    0.59
    ArgsConstructor
    0.59
    fjspx
    0.56
     IndexPath
    0.54
    couvrez
    0.53
     BoxDecoration
    0.52
    CGRectMake
    0.52
    Activations Density 0.220%

    No Known Activations