© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8718
    Prev
    Next
    INDEX
    Explanations

    words related to science or medicine, in particular about how to diagnose or treat diseases or other problems

    oai_token-act-pair · gemini-2.0-flash

    protein

    np_max-act-logits · gemini-2.0-flash

    say "space" words Method used: 2 — because following tokens mostly start with a leading space; say "space" words

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    omeness
    -0.28
    tabIndex
    -0.26
    setRequest
    -0.24
    ssant
    -0.23
    tedly
    -0.22
    tely
    -0.22
    ات
    -0.22
    cki
    -0.22
    gensen
    -0.21
    èle
    -0.21
    POSITIVE LOGITS
    encounter
    0.72
    afternoon
    0.71
    representative
    0.70
    potential
    0.70
    enthusi
    0.69
    domestic
    0.68
    presence
    0.68
    consumption
    0.68
    correspond
    0.67
    maintenance
    0.67
    Activations Density 51.319%

    No Known Activations