© 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. 13800
    Prev
    Next
    INDEX
    Explanations

    varied markup and formulaic content within technical documents

    oai_token-act-pair · gemini-2.0-flash

    Colons and "his"

    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
    itinéraire
    -0.64
    ViewImports
    -0.61
    Schedulers
    -0.56
    蜒
    -0.55
    featureID
    -0.54
     Koo
    -0.53
    BufferException
    -0.52
    Datuak
    -0.52
    nestjs
    -0.52
    }();
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.54
    最快更新
    0.50
    ::_('
    0.46
     الحره
    0.43
    dotenv
    0.43
    期刊论文
    0.42
    RTEE
    0.42
    ostante
    0.42
     appartamento
    0.41
    ----</
    0.41
    Activations Density 0.925%

    No Known Activations