© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9941
    Prev
    Next
    INDEX
    Explanations

    strings of danish words along with parenthesis and numbers

    oai_token-act-pair · gemini-2.0-flash

    bt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    uxxxx
    -0.73
    makeConstraints
    -0.53
     оригіналу
    -0.53
    devamını
    -0.51
    ksikon
    -0.48
    gige
    -0.46
    BeginInit
    -0.45
    migrationBuilder
    -0.45
    setViewportView
    -0.44
    UnusedPrivate
    -0.44
    POSITIVE LOGITS
    MessageOf
    0.70
     initComponents
    0.66
     كومونز
    0.63
     bygget
    0.54
    Gizmos
    0.53
    WithMany
    0.52
    dbo
    0.52
    rdquo
    0.50
    RTGC
    0.50
     demografica
    0.50
    Activations Density 1.088%

    No Known Activations