© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258079
    Prev
    Next
    INDEX
    Explanations

    private, sperm, everything, avoid, sum

    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_22_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
     معنى
    0.43
     Держа
    0.42
     Trouvez
    0.41
     লেখা
    0.39
     Durant
    0.39
     Introduced
    0.39
    s
    0.39
     Scholar
    0.39
     operands
    0.39
    瓒
    0.39
    POSITIVE LOGITS
     diá
    0.44
    났다
    0.44
    ुट
    0.43
     hamil
    0.42
     adrenalin
    0.42
     houve
    0.41
     benign
    0.40
     occured
    0.40
     liggen
    0.40
     docker
    0.40
    Activations Density 0.000%

    No Known Activations