© 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. 156669
    Prev
    Next
    INDEX
    Explanations

    shikamate pathway

    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
    ０
    1.23
    ม
    1.23
     oiseaux
    1.10
     espèces
    1.07
     azienda
    1.07
    к
    1.05
     équipes
    1.04
    1.02
     anciens
    0.99
    лло
    0.98
    POSITIVE LOGITS
    c
    1.60
    X
    1.48
    J
    1.44
    IN
    1.38
    ang
    1.37
    ED
    1.34
    t
    1.32
    Table
    1.31
    ab
    1.30
    a
    1.30
    Activations Density 0.001%

    No Known Activations