© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237223
    Prev
    Next
    INDEX
    Explanations

    doing actions or similar things

    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_32_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
     пробу
    0.41
     borrar
    0.40
     infrequent
    0.38
     setTasks
    0.38
     ataques
    0.37
    ској
    0.36
     Punkten
    0.36
    蛜
    0.36
     завдання
    0.36
    点を
    0.36
    POSITIVE LOGITS
     بكل
    0.38
    ListenAnd
    0.35
    fra
    0.34
     grin
    0.34
    ʌ
    0.34
     bezier
    0.34
    ifikat
    0.34
    sleep
    0.33
     पार्टनर
    0.33
     piş
    0.33
    Activations Density 0.003%

    No Known Activations