© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    scriptable Objects

    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
     EventArgs
    1.85
    z
    1.75
    zis
    1.70
    ACC
    1.67
    jacket
    1.63
    INSERT
    1.63
     AG
    1.55
     piston
    1.55
    netfx
    1.53
    績
    1.53
    POSITIVE LOGITS
    ный
    1.93
    ется
    1.75
    מונה
    1.75
    ส์
    1.74
    ik
    1.71
     चलो
    1.69
    ें
    1.67
    
    1.66
     ऐसे
    1.64
    ا
    1.64
    Activations Density 0.000%

    No Known Activations