© 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. 6335
    Prev
    Next
    INDEX
    Explanations

    oven rack or wire rack

    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
     Ï
    0.97
    джа
    0.92
     InputStream
    0.92
    ं
    0.89
    ことができます
    0.88
    ных
    0.86
    습니다
    0.84
    ヤー
    0.84
    ال
    0.83
    shore
    0.83
    POSITIVE LOGITS
     stints
    0.91
     lượt
    0.86
    ity
    0.83
    ат
    0.79
    ע
    0.77
    ित
    0.77
    की
    0.76
    olar
    0.75
     pues
    0.75
    _,
    0.74
    Activations Density 0.001%

    No Known Activations