© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    /en/ web paths

    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
    του
    0.45
     eng
    0.40
    サスカ
    0.40
    룺
    0.40
    北大
    0.40
     تاريخ
    0.39
     intend
    0.39
     tú
    0.38
     পার্থক্য
    0.38
     ಸ್
    0.38
    POSITIVE LOGITS
    percayaan
    0.40
    perity
    0.37
    酲
    0.37
     Knife
    0.36
    Pane
    0.35
     /-
    0.35
    たま
    0.35
     Lep
    0.34
    ग्रह
    0.34
    /',
    0.34
    Activations Density 0.003%

    No Known Activations