© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7936
    Prev
    Next
    INDEX
    Explanations

    guidelines and specific topics

    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
     preparing
    0.18
     allocating
    0.18
     separating
    0.18
     in
    0.17
    宻
    0.17
     adapting
    0.17
    (*
    0.17
     elementary
    0.16
    IDEA
    0.16
     leaving
    0.16
    POSITIVE LOGITS
    ྐ
    0.21
     lorf
    0.20
    ្ប
    0.20
    স্পতিবার
    0.19
     steamers
    0.19
    urón
    0.19
    abri
    0.19
     Spani
    0.19
    ަރު
    0.19
     சனி
    0.19
    Activations Density 0.076%

    No Known Activations