© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4437
    Prev
    Next
    INDEX
    Explanations

    clauses that contrast items

    oai_token-act-pair · gemini-2.0-flash

    qualifications and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     uns
    -0.56
    vaal
    -0.51
    uncios
    -0.50
    complexType
    -0.49
     Hal
    -0.48
     HasFactory
    -0.48
    moveToFirst
    -0.48
    enzen
    -0.48
    IsVisible
    -0.47
     Kam
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.81
     समीक्षाओं
    0.65
     المعيارى
    0.63
    contentLoaded
    0.61
     незавершена
    0.60
    mybatisplus
    0.58
    BeginContext
    0.57
    PMailer
    0.54
     BytesLike
    0.53
    ClientSize
    0.52
    Activations Density 2.526%

    No Known Activations