© 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. 126681
    Prev
    Next
    INDEX
    Explanations

    googleapis.com links or Greek words

    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
     amd
    0.68
     arid
    0.66
    ă
    0.65
     lanz
    0.63
     ي
    0.63
     baños
    0.61
    ليب
    0.60
     appel
    0.59
     Spielberg
    0.59
     at
    0.59
    POSITIVE LOGITS
    t
    0.76
    ec
    0.71
    den
    0.69
    da
    0.68
    p
    0.66
    ate
    0.65
    ori
    0.64
    ون
    0.64
    there
    0.64
    dain
    0.64
    Activations Density 0.001%

    No Known Activations