© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12160
    Prev
    Next
    INDEX
    Explanations

    various punctuation symbols, words related to the word "break", and the word "outlined"

    oai_token-act-pair · gemini-2.0-flash

    say "IN"

    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
     in
    -1.63
    ใน
    -0.93
     dalam
    -0.89
     trong
    -0.77
     في
    -0.72
    migrationBuilder
    -0.71
    ⓧ
    -0.71
     فى
    -0.71
    Dalam
    -0.69
    CompleteListener
    -0.67
    POSITIVE LOGITS
    IN
    0.54
    inv
    0.50
    Inv
    0.48
    ÍN
    0.46
    INAR
    0.45
    AddWithValue
    0.45
    ICLE
    0.45
     diting
    0.44
     en
    0.44
    ovina
    0.43
    Activations Density 2.984%

    No Known Activations