© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13437
    Prev
    Next
    INDEX
    Explanations

    mentions of people serving in an official capacity for an organization

    oai_token-act-pair · gemini-2.0-flash

    professional titles or roles

    np_token-act-pair-logits · gpt-4o-mini

    organizations and leadership

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    VideoCapture
    -0.46
     Pili
    -0.44
     mío
    -0.43
    ences
    -0.43
    wpi
    -0.42
    Personendaten
    -0.41
    BeginContext
    -0.41
     *((
    -0.40
     esser
    -0.40
    mathop
    -0.39
    POSITIVE LOGITS
    出版年
    0.76
    MigrationBuilder
    0.69
     useAppContext
    0.57
     Audiodateien
    0.56
     Executive
    0.56
    EXECUTIVE
    0.55
    Abitanti
    0.54
     courbe
    0.54
    toHaveBeenCalled
    0.53
     Moderator
    0.53
    Activations Density 3.204%

    No Known Activations