© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8115
    Prev
    Next
    INDEX
    Explanations

    a wide variety of common words, seemingly with no rhyme or reason

    oai_token-act-pair · gemini-2.0-flash

    record

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     market
    -0.96
     Market
    -0.95
    market
    -0.93
    Market
    -0.85
     MARKET
    -0.76
     markets
    -0.73
    MARKET
    -0.66
     Markets
    -0.65
     Markt
    -0.65
    市场
    -0.60
    POSITIVE LOGITS
     record
    0.76
     Record
    0.73
     records
    0.71
     RECORDS
    0.69
     RECORD
    0.69
    Records
    0.68
     Records
    0.66
    record
    0.66
    Record
    0.66
    ειτουργ
    0.66
    Activations Density 5.773%

    No Known Activations