© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123836
    Prev
    Next
    INDEX
    Explanations

    define abbreviations

    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
    I
    0.73
    .
    0.71
    ς
    0.68
    verted
    0.67
    S
    0.67
    et
    0.66
    oitte
    0.62
    iteit
    0.61
    zzel
    0.61
    etar
    0.61
    POSITIVE LOGITS
    m
    0.70
    ן
    0.68
    p
    0.67
    ла
    0.63
     mette
    0.61
    ’
    0.57
    ం
    0.55
     corresponde
    0.55
     Spectra
    0.55
    iu
    0.54
    Activations Density 0.001%

    No Known Activations