© 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. 5602
    Prev
    Next
    INDEX
    Explanations

    .com context

    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
     holomorphic
    0.84
     homomorphism
    0.83
    osing
    0.83
    ৮
    0.81
    upaten
    0.81
    től
    0.80
     seguramente
    0.77
     guvern
    0.77
    tenance
    0.77
    ee
    0.75
    POSITIVE LOGITS
    ️
    1.22
    ம்
    1.06
    л
    0.96
    an
    0.91
    jenigen
    0.89
    ****************
    0.83
    ה
    0.82
    ת
    0.82
    at
    0.82
     gotta
    0.81
    Activations Density 0.198%

    No Known Activations