© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15274
    Prev
    Next
    INDEX
    Explanations

    the word 'cable'

    oai_token-act-pair · gemini-2.0-flash

    cable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    脚注の使い方
    -1.30
     defaultstate
    -1.14
     ویکی‌پدیای
    -1.08
    rungsseite
    -1.05
    expandindo
    -1.05
     للاسماء
    -1.02
    UnsafeEnabled
    -0.97
    tagHelperRunner
    -0.95
    providedIn
    -0.95
    tvguidetime
    -0.95
    POSITIVE LOGITS
    й
    0.60
    kela
    0.57
     the
    0.56
    kel
    0.55
     a
    0.54
     alle
    0.53
     ghi
    0.52
    e
    0.52
     rol
    0.52
     kem
    0.52
    Activations Density 1.310%

    No Known Activations