© 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. 14272
    Prev
    Next
    INDEX
    Explanations

    document headers or metadata and tags

    oai_token-act-pair · gemini-2.0-flash

    title description

    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
    Cie
    -0.48
    క్ష
    -0.47
     Ballot
    -0.46
     Samba
    -0.45
    vor
    -0.44
    FontOfSize
    -0.44
    üb
    -0.44
    BagConstraints
    -0.43
    za
    -0.43
    спа
    -0.43
    POSITIVE LOGITS
    клопе
    0.67
     समीक्षाओं
    0.64
     समीक्षक
    0.54
    verwijspagina
    0.54
     kasarigan
    0.53
    homonymie
    0.52
     EconPapers
    0.49
     nahilalakip
    0.49
     שוליים
    0.49
    קישורים
    0.48
    Activations Density 0.113%

    No Known Activations