© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38163
    Prev
    Next
    INDEX
    Explanations

    Susie Ellis, Susie Ghahremani, PlanetSuzy

    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
    ονται
    0.76
    _
    0.71
     be
    0.71
    s
    0.69
    illers
    0.68
    2
    0.66
     frío
    0.65
    ش
    0.64
    for
    0.62
     extracción
    0.62
    POSITIVE LOGITS
    -
    0.93
    ය
    0.73
    ’
    0.68
    nelle
    0.65
     አንዳንድ
    0.65
    -<
    0.65
    }",
    0.63
    יות
    0.63
    ियों
    0.62
    وم
    0.62
    Activations Density 0.009%

    No Known Activations