© 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. 246752
    Prev
    Next
    INDEX
    Explanations

    .env and configuration files

    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
     adres
    0.41
     퇴
    0.39
    adios
    0.39
     addressed
    0.38
     ચંદ્ર
    0.38
    сток
    0.37
     Gild
    0.36
     সিংহের
    0.36
    笾
    0.36
     leggings
    0.35
    POSITIVE LOGITS
    AUT
    0.45
    KEY
    0.44
    Key
    0.44
    Path
    0.43
    key
    0.39
    Aut
    0.38
    path
    0.38
     Key
    0.37
     Path
    0.37
    Trader
    0.36
    Activations Density 0.001%

    No Known Activations