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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124855
    Prev
    Next
    INDEX
    Explanations

    eviction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    2
    1.03
    ال
    0.89
    média
    0.73
    bans
    0.73
    pora
    0.71
    тья
    0.69
    9
    0.69
    person
    0.68
    lja
    0.67
    жами
    0.67
    POSITIVE LOGITS
    ו
    0.89
    ες
    0.78
    й
    0.73
     don
    0.73
     escrib
    0.72
     wasn
    0.69
    {
    0.68
    {'
    0.64
    <0x80>
    0.63
    ອກ
    0.63
    Activations Density 0.002%

    No Known Activations