© 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. 6623
    Prev
    Next
    INDEX
    Explanations

    API, example, mapped

    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
    ন
    0.78
    िक
    0.71
    +","+
    0.66
     legumes
    0.66
     endast
    0.64
     изуча
    0.64
     semiconductor
    0.64
     oppress
    0.63
    diagnostic
    0.62
    ➢
    0.62
    POSITIVE LOGITS
    ру
    0.73
    are
    0.67
    ा
    0.63
    땐
    0.59
    ઓમાં
    0.58
     prized
    0.57
    𝘬
    0.57
    以
    0.57
     crit
    0.56
    ро
    0.55
    Activations Density 0.000%

    No Known Activations