© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48663
    Prev
    Next
    INDEX
    Explanations

    pockets and compartments

    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_31_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
    makarna
    0.41
     अरो
    0.36
     ternary
    0.35
     बहादुर
    0.35
     gliding
    0.35
    quadratic
    0.35
     Psychology
    0.34
    ",[],"
    0.34
    imester
    0.34
     чолові
    0.34
    POSITIVE LOGITS
    pret
    0.40
    Sin
    0.40
     信
    0.40
     Sin
    0.39
     Pret
    0.39
    Come
    0.39
     SIN
    0.39
    Cel
    0.38
     Come
    0.38
     귀
    0.38
    Activations Density 0.002%

    No Known Activations