© 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. 124809
    Prev
    Next
    INDEX
    Explanations

    push_back

    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
    ו
    0.72
    お
    0.67
    I
    0.66
    (
    0.62
    0.61
    0
    0.59
    お得
    0.59
    </strong>
    0.58
     "/
    0.58
    場合は
    0.57
    POSITIVE LOGITS
     to
    0.70
    ون
    0.69
    ناسب
    0.69
    లో
    0.66
    sman
    0.65
    äär
    0.63
    ,
    0.63
    ské
    0.63
     korun
    0.63
    nél
    0.63
    Activations Density 0.000%

    No Known Activations