© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12494
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words associated with business contexts, particularly transportation and finance, as well as parenthetical phrases of comma separated words

    oai_token-act-pair · gemini-2.0-flash

    coach

    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
     utafitiHapana
    -0.84
    +:+
    -0.74
    HasAnnotation
    -0.67
    եռ
    -0.63
    ContentAsync
    -0.63
    httphttps
    -0.62
    uxxxx
    -0.60
    Odkazy
    -0.59
    rungsseite
    -0.59
    WireFormat
    -0.59
    POSITIVE LOGITS
     coaches
    1.00
     coach
    0.98
     Coaches
    0.93
     Coach
    0.92
    Coach
    0.88
     motor
    0.85
     COACH
    0.83
    coach
    0.80
     bus
    0.79
    Coaches
    0.75
    Activations Density 1.267%

    No Known Activations