© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90985
    Prev
    Next
    INDEX
    Explanations

    pending

    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_11_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
    on
    0.87
    is
    0.69
    ي
    0.60
    i
    0.59
    by
    0.59
    ously
    0.56
     on
    0.56
    un
    0.55
    性
    0.54
     csak
    0.53
    POSITIVE LOGITS
     actualizado
    0.56
     Organizations
    0.55
     Landscapes
    0.55
    دد
    0.54
    RECENT
    0.54
     단계
    0.53
    𝗔
    0.53
    तावनी
    0.52
    OURCES
    0.52
     ambito
    0.52
    Activations Density 0.028%

    No Known Activations