© 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. 45435
    Prev
    Next
    INDEX
    Explanations

    lists of questions or points

    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
    彆
    0.27
    ಾಂ
    0.26
     boundaries
    0.25
     lesbians
    0.25
    november
    0.25
    reflected
    0.25
    ontaneous
    0.25
     marginalised
    0.24
    boundaries
    0.24
    nless
    0.23
    POSITIVE LOGITS
     Анг
    0.29
    就可以了
    0.26
    ጼ
    0.25
     При
    0.24
     Curling
    0.24
     Кри
    0.24
     Jacobi
    0.24
    ारी
    0.24
     tricycle
    0.23
     Джек
    0.23
    Activations Density 0.034%

    No Known Activations