© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5359
    Prev
    Next
    INDEX
    Explanations

    the following word

    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
    an
    1.58
    ️
    1.39
    ת
    1.29
    ان
    1.28
    ோ
    1.25
    ي
    1.25
    ২০
    1.13
    า
    1.12
    ారు
    1.11
    बिहार
    1.11
    POSITIVE LOGITS
    dır
    1.07
     reuse
    1.03
    cas
    1.03
    cula
    1.02
    culas
    0.96
    cule
    0.95
     é
    0.95
     iar
    0.94
     reachable
    0.94
    pyrazol
    0.93
    Activations Density 0.061%

    No Known Activations