© 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. 35957
    Prev
    Next
    INDEX
    Explanations

    GRE SAT ACT writing reasoning questions

    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
    in
    0.14
     푸
    0.13
    lą
    0.12
     sommet
    0.12
     εισ
    0.12
     लड़कियों
    0.12
     호
    0.11
    լ
    0.11
    Σ
    0.11
    д
    0.11
    POSITIVE LOGITS
    Какие
    0.13
    놁
    0.13
    agnar
    0.12
    ровкой
    0.12
    нор
    0.12
     někter
    0.12
    otele
    0.11
     totally
    0.11
     beep
    0.11
     narcotic
    0.11
    Activations Density 0.002%

    No Known Activations