© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    Linux distributions

    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_5_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
    ं
    1.91
    ur
    1.87
    em
    1.87
    te
    1.79
    im
    1.74
    ѕ
    1.70
    us
    1.68
    ির
    1.67
    ab
    1.65
    un
    1.65
    POSITIVE LOGITS
     elution
    2.00
     jaw
    1.95
     banter
    1.94
     jabs
    1.94
     choirs
    1.87
     AgNO
    1.84
     elicited
    1.84
    腚
    1.83
     cements
    1.83
    😧
    1.82
    Activations Density 0.000%

    No Known Activations