© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40570
    Prev
    Next
    INDEX
    Explanations

    operator

    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
    "，
    0.61
    Ⅺ
    0.54
    ИН
    0.54
    膂
    0.53
    เตอร์
    0.52
    धपुर
    0.52
     Therapeutic
    0.51
    LOADSTRING
    0.51
    剽
    0.50
     অনুষ্ঠিত
    0.49
    POSITIVE LOGITS
    otros
    0.62
     databases
    0.61
     awe
    0.61
     arrays
    0.59
    ook
    0.59
     flock
    0.58
     zwr
    0.57
    ows
    0.57
     chronicles
    0.56
    otic
    0.55
    Activations Density 0.000%

    No Known Activations