© 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. 7093
    Prev
    Next
    INDEX
    Explanations

    ISRU, ISRS, ISRF, ISFP

    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
    ্দ
    2.20
     번째
    2.05
    ্স
    2.03
    hams
    2.00
    된
    1.99
    !\!\
    1.89
    egaard
    1.87
     Ці
    1.82
    nonzero
    1.82
    wicket
    1.79
    POSITIVE LOGITS
     faut
    2.14
     incontinence
    2.13
    та
    2.13
    ح
    2.04
    dtypes
    1.98
     потре
    1.97
     êtres
    1.96
     confisc
    1.93
     penduduk
    1.92
     croissants
    1.91
    Activations Density 0.002%

    No Known Activations