© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13533
    Prev
    Next
    INDEX
    Explanations

    places where comparisons are being made between different items

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     publiques
    -0.55
     aient
    -0.52
     inalámb
    -0.49
     mecán
    -0.48
     enfans
    -0.48
     NDEBUG
    -0.45
    ็
    -0.44
    mappedBy
    -0.44
     culturelles
    -0.44
    TintMode
    -0.42
    POSITIVE LOGITS
    BuildContext
    0.66
    principalTable
    0.58
     defaultstate
    0.56
    yargs
    0.56
    elemField
    0.55
    <?>>
    0.52
     lược
    0.52
    Explicación
    0.51
    </tfoot>
    0.50
    anguages
    0.50
    Activations Density 2.445%

    No Known Activations