© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13110
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    say period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     AssemblyCulture
    -1.80
     تضيفلها
    -1.72
    MigrationBuilder
    -1.65
    rungsseite
    -1.63
     متعلقه
    -1.63
     nahilalakip
    -1.62
    IntoConstraints
    -1.62
    DockStyle
    -1.59
    parsedMessage
    -1.59
     Efq
    -1.57
    POSITIVE LOGITS
    3
    0.86
    2
    0.85
    ,
    0.85
    1
    0.84
    6
    0.79
    .
    0.78
    -
    0.74
    5
    0.72
    ↵
    0.71
    9
    0.69
    Activations Density 17.080%

    No Known Activations