© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12231
    Prev
    Next
    INDEX
    Explanations

    context involving theories, models, historical time, or business offerings within a document.

    oai_token-act-pair · 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
     виправивши
    -0.73
    ⓘ
    -0.67
    ValueStyle
    -0.66
     compared
    -0.65
     pinulongan
    -0.64
    SourceChecksum
    -0.64
    Compared
    -0.63
     Compared
    -0.60
    EDEFAULT
    -0.60
     nahilalakip
    -0.59
    POSITIVE LOGITS
     also
    0.52
    also
    0.48
    更是
    0.47
    ReusableCell
    0.47
     {}".
    0.46
    でもあります
    0.45
    همچنین
    0.44
     Also
    0.44
     INTERESAR
    0.44
     أيضاً
    0.43
    Activations Density 6.680%

    No Known Activations