© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197514
    Prev
    Next
    INDEX
    Explanations

    inventory

    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_4_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
    ስማ
    0.88
    ን
    0.86
    ;
    0.85
     innovative
    0.82
     frantically
    0.80
     ingenuity
    0.80
    ্স
    0.80
     mesmas
    0.80
    夂
    0.80
     וא
    0.79
    POSITIVE LOGITS
    at
    1.14
    Inventory
    1.00
    (
    0.97
    2
    0.97
     Inventory
    0.95
    ong
    0.95
    re
    0.88
    ur
    0.88
    inventory
    0.85
    다
    0.85
    Activations Density 0.001%

    No Known Activations