© 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. 5483
    Prev
    Next
    INDEX
    Explanations

    Marvel or Dragons

    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
     microseconds
    1.04
    غ
    1.02
    ش
    0.99
    }$)
    0.95
    ேயே
    0.92
    g
    0.90
    (\
    0.88
    }$).
    0.88
    }$:
    0.86
    是从
    0.83
    POSITIVE LOGITS
    nung
    1.09
    ин
    1.01
     tangential
    1.00
    ஞ்ஞான
    0.98
     число
    0.95
    िया
    0.95
    asjon
    0.94
     poodle
    0.94
     bfs
    0.93
     hinged
    0.93
    Activations Density 0.015%

    No Known Activations