© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137303
    Prev
    Next
    INDEX
    Explanations

    flower spike

    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_12_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
     содержи
    0.64
    偣
    0.63
     выращи
    0.62
    㖑
    0.62
    圿
    0.61
     SGA
    0.59
     советы
    0.59
    絽
    0.58
     tomate
    0.57
    🥗
    0.57
    POSITIVE LOGITS
    ack
    0.69
    lasting
    0.60
    aw
    0.59
    ancer
    0.57
    mechan
    0.57
    frame
    0.56
    acking
    0.56
    que
    0.55
    uk
    0.55
    that
    0.55
    Activations Density 0.000%

    No Known Activations