© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4259
    Prev
    Next
    INDEX
    Explanations

    code and data manipulation

    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_40_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
    [
    1.05
    ()[
    0.85
    )[
    0.73
    _[
    0.73
    ')[
    0.72
    '][
    0.71
    ")[
    0.68
    $[
    0.67
    }[
    0.67
    。[
    0.66
    POSITIVE LOGITS
     eagle
    0.42
     lệch
    0.38
     offence
    0.38
     श्रम
    0.38
    Eagle
    0.36
     বল
    0.36
     <?
    0.36
    ेंज
    0.35
     Eagle
    0.35
     terve
    0.35
    Activations Density 0.082%

    No Known Activations