© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8137
    Prev
    Next
    INDEX
    Explanations

    string data type declarations

    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
    ة
    1.17
    candles
    1.08
    ed
    1.03
    y
    0.99
    ا
    0.99
    ش
    0.98
    ب
    0.98
    yaj
    0.98
    िक
    0.92
    ు
    0.87
    POSITIVE LOGITS
    ر
    1.09
     stellen
    1.03
    ک
    0.99
    ána
    0.99
    ур
    0.97
    ﻲ
    0.96
    뻣
    0.96
     skyrocketed
    0.96
    WARD
    0.95
    eel
    0.94
    Activations Density 0.018%

    No Known Activations