© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1776
    Prev
    Next
    INDEX
    Explanations

    statements of possibility or difficulty, often in a business context

    oai_token-act-pair · gemini-2.0-flash

    formal and business language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    StructEnd
    -0.66
     ModelExpression
    -0.64
    ГЛА
    -0.59
    EndContext
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    BindView
    -0.56
    AutoScaleMode
    -0.56
     clearColor
    -0.54
     виправивши
    -0.52
    istoitu
    -0.52
    POSITIVE LOGITS
    LinkId
    0.55
    TintMode
    0.50
    CodeDom
    0.48
    livejournal
    0.48
    al
    0.47
     word
    0.47
     Word
    0.47
     aluminum
    0.46
     service
    0.45
    *************/
    0.45
    Activations Density 1.932%

    No Known Activations