© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    capitalized words in business and technical contexts

    oai_token-act-pair · gemini-2.0-flash

    Formal/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     e
    -0.47
     v
    -0.46
     of
    -0.45
    C
    -0.43
     A
    -0.43
     (
    -0.42
     C
    -0.42
    ↵
    -0.42
    (
    -0.41
    A
    -0.41
    POSITIVE LOGITS
    OGND
    1.21
    \{\\
    1.09
     Roskov
    1.02
     للاسماء
    1.00
    +#+
    0.96
    קישורים
    0.95
    Hentet
    0.93
     незавершена
    0.90
     تضيفلها
    0.89
    Personensuche
    0.88
    Activations Density 2.305%

    No Known Activations