© 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. 14578
    Prev
    Next
    INDEX
    Explanations

    numbers and number-like strings

    oai_token-act-pair · gemini-2.0-flash

    say "7"

    np_max-act-logits · gemini-2.0-flash

    say "7" Method used: 2 — because every token after the max activating token is 7 — say "7"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Seven
    -1.09
     Seven
    -1.06
    seven
    -1.02
     seven
    -0.98
     seventh
    -0.96
    SEVEN
    -0.95
     SEVEN
    -0.95
     eighth
    -0.91
    VII
    -0.89
     Seventh
    -0.87
    POSITIVE LOGITS
    Autoritní
    0.82
     незавершена
    0.82
     الرياضيه
    0.70
    neté
    0.68
    SPATH
    0.67
    Portail
    0.67
     AssemblyCulture
    0.65
    клопе
    0.62
    InjectAttribute
    0.62
     Abp
    0.59
    Activations Density 6.235%

    No Known Activations