© 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. 13363
    Prev
    Next
    INDEX
    Explanations

    code or mixed-language filenames including forward slashes

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    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
    DockStyle
    -0.67
    LookAnd
    -0.63
    CloseOperation
    -0.52
     ComVisible
    -0.52
    awtextra
    -0.51
    MigrationBuilder
    -0.50
    IsContent
    -0.48
    UnusedPrivate
    -0.47
     defaultstate
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
    ary
    0.82
    mun
    0.81
    vo
    0.80
    ato
    0.79
    ma
    0.79
    le
    0.79
    var
    0.79
    ke
    0.78
    ig
    0.77
    chi
    0.77
    Activations Density 2.966%

    No Known Activations