© 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. 90263
    Prev
    Next
    INDEX
    Explanations

    wandered into a

    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
     to
    0.86
     as
    0.79
     from
    0.79
     at
    0.68
     on
    0.68
    ن
    0.67
    elt
    0.67
     Wonder
    0.67
     of
    0.66
    ח
    0.66
    POSITIVE LOGITS
    s
    0.74
    they
    0.72
    suggestions
    0.67
    så
    0.65
    determine
    0.64
    that
    0.63
    schl
    0.62
    If
    0.61
    saw
    0.61
    sensing
    0.61
    Activations Density 0.001%

    No Known Activations