© 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. 15782
    Prev
    Next
    INDEX
    Explanations

    words or phrases that could be titles, particularly scientific ones.

    oai_token-act-pair · 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
    writeFieldEnd
    -0.56
     financières
    -0.52
    ldc
    -0.50
    GenerationType
    -0.50
    sidemargin
    -0.48
     folosit
    -0.46
    fortawesome
    -0.46
    protoc
    -0.45
    дца
    -0.44
    stringify
    -0.44
    POSITIVE LOGITS
    ("")]
    0.74
    TestingModule
    0.73
     nahilalakip
    0.71
    Архівовано
    0.69
    tvguidetime
    0.64
    NameInMap
    0.63
    PreferredItem
    0.63
     상세
    0.62
    QMetaType
    0.61
    허
    0.59
    Activations Density 52.461%

    No Known Activations