© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6362
    Prev
    Next
    INDEX
    Explanations

    list, bullet point

    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
     minded
    0.70
    йт
    0.61
    是要
    0.58
    ະ
    0.57
    ﺄ
    0.57
    槃
    0.57
    minded
    0.54
     banana
    0.54
    ante
    0.53
    忡
    0.52
    POSITIVE LOGITS
     khử
    0.67
    बिनेट
    0.65
    ς
    0.64
    യ
    0.62
    Substituting
    0.60
    surgical
    0.59
    ات
    0.59
     '.')
    0.58
    Effects
    0.58
     Quantification
    0.58
    Activations Density 2.838%

    No Known Activations