© 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. 124605
    Prev
    Next
    INDEX
    Explanations

    woodchucksMackenzieWoods Hole

    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
     in
    0.94
    ти
    0.93
    s
    0.80
     coffers
    0.74
    𝘢
    0.63
     for
    0.63
    ну
    0.63
    on
    0.63
    то
    0.63
     erotic
    0.61
    POSITIVE LOGITS
    I
    0.68
    req
    0.65
    }}=\
    0.65
    quarters
    0.65
    ac
    0.63
    Z
    0.63
    that
    0.62
    com
    0.59
    call
    0.59
    عمل
    0.59
    Activations Density 0.000%

    No Known Activations