© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198946
    Prev
    Next
    INDEX
    Explanations

    achieve its original goals

    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_9_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
    0.52
    :
    0.52
     chiral
    0.50
    experimental
    0.48
     jockey
    0.46
    Classification
    0.45
    𒈠
    0.45
    inol
    0.45
    inic
    0.45
    ARRANT
    0.45
    POSITIVE LOGITS
    Чтобы
    0.54
    वणे
    0.50
    Бо
    0.46
    茫
    0.46
    वत्ता
    0.45
     Espresso
    0.45
    ibuya
    0.44
    Боль
    0.43
    駑
    0.42
     době
    0.42
    Activations Density 0.000%

    No Known Activations