© 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. 34808
    Prev
    Next
    INDEX
    Explanations

    straightforward

    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
    ר
    0.80
    র
    0.75
    ر
    0.70
    ア
    0.70
    ক
    0.68
    ם
    0.66
    ל
    0.66
     was
    0.64
     at
    0.63
     вста
    0.63
    POSITIVE LOGITS
    that
    0.70
    {
    0.67
    k
    0.61
    h
    0.57
    with
    0.53
    (“
    0.53
    <sup>
    0.52
     Challeng
    0.52
    soever
    0.51
     Rubin
    0.51
    Activations Density 0.008%

    No Known Activations