© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5572
    Prev
    Next
    INDEX
    Explanations

    numbers or variables after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irreducible
    1.03
    ം
    0.99
     exertion
    0.95
    িং
    0.94
     exfoliating
    0.92
     exfoli
    0.90
    "*
    0.88
     putea
    0.86
    د
    0.85
    tik
    0.85
    POSITIVE LOGITS
    rta
    1.06
    ர்
    0.98
    r
    0.97
    at
    0.95
    russ
    0.94
    rda
    0.93
    ong
    0.92
    ang
    0.91
    ●
    0.89
    ның
    0.88
    Activations Density 0.042%

    No Known Activations