© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15701
    Prev
    Next
    INDEX
    Explanations

    the phrase "at this point."

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    XtraBars
    -0.70
     ویکی‌پدیا
    -0.69
     Roskov
    -0.67
     createState
    -0.67
     كومونز
    -0.66
    DockStyle
    -0.63
    migrationBuilder
    -0.55
    abestanden
    -0.53
     intptr
    -0.52
    SequentialGroup
    -0.52
    POSITIVE LOGITS
    EndProject
    0.69
    ôtel
    0.59
    MigrationBuilder
    0.59
    новниш
    0.58
    Controllo
    0.56
    Traducción
    0.56
    itespace
    0.53
     Latte
    0.51
     nameof
    0.50
     esat
    0.48
    Activations Density 1.101%

    No Known Activations