© 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. 43558
    Prev
    Next
    INDEX
    Explanations

    tools, thailand, tattoo, madre, manual

    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
    ک
    0.94
    کلی
    0.69
    ες
    0.67
    AUC
    0.67
    M
    0.67
     اکرم
    0.66
    REZ
    0.66
    ام
    0.65
    وری
    0.63
     밝혔
    0.63
    POSITIVE LOGITS
    р
    0.75
    то
    0.70
    to
    0.66
     das
    0.65
    ,
    0.63
    '
    0.63
    ш
    0.63
    й
    0.63
     fourn
    0.59
     garant
    0.59
    Activations Density 0.000%

    No Known Activations