© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35093
    Prev
    Next
    INDEX
    Explanations

    animals and species names

    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_7_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
    as
    0.86
    an
    0.74
    ne
    0.72
    1
    0.72
    y
    0.72
    at
    0.66
    os
    0.64
    ina
    0.64
    ec
    0.63
    ul
    0.62
    POSITIVE LOGITS
     το
    0.73
    كتب
    0.67
     يا
    0.66
     flies
    0.66
     ότι
    0.65
    ﺷ
    0.64
     أو
    0.64
    த்ய
    0.64
     لكن
    0.64
     दट
    0.64
    Activations Density 0.027%

    No Known Activations