© 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. 141424
    Prev
    Next
    INDEX
    Explanations

    pool balls collision

    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
    á
    0.42
    infl
    0.41
     foam
    0.41
     exotic
    0.40
     square
    0.40
     kefir
    0.39
     $
    0.38
     spinal
    0.38
    apai
    0.38
     "
    0.37
    POSITIVE LOGITS
     год
    0.49
    ດ້ວຍ
    0.46
     получи
    0.45
     ده
    0.44
    డ్
    0.44
    อม
    0.44
     वैलेंट
    0.43
     보내
    0.43
     देव
    0.43
     созда
    0.43
    Activations Density 0.001%

    No Known Activations