© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111917
    Prev
    Next
    INDEX
    Explanations

    Kill la Kill, launder, launch, lapping

    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_2_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
    는
    1.46
    لي
    1.38
     to
    1.16
    是
    1.12
    ৮
    1.05
     maggio
    1.04
    но
    1.03
     maio
    1.02
     riguarda
    1.01
     noastră
    1.01
    POSITIVE LOGITS
    ir
    1.56
    ers
    1.51
    ان
    1.40
    il
    1.34
    ુ
    1.31
    ar
    1.30
    ies
    1.26
    en
    1.23
    te
    1.23
    et
    1.22
    Activations Density 0.000%

    No Known Activations