© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136349
    Prev
    Next
    INDEX
    Explanations

    crossword clues

    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
    ost
    0.54
     predicates
    0.53
    ism
    0.52
    اً
    0.51
    ü
    0.50
    alliative
    0.50
    ating
    0.49
    igheden
    0.48
     revolved
    0.48
    ط
    0.48
    POSITIVE LOGITS
     scoff
    0.58
    Judge
    0.57
    Tar
    0.57
     konser
    0.57
     bulundu
    0.57
     gostaria
    0.55
     belirli
    0.55
     tako
    0.54
    Wiki
    0.54
     toNumber
    0.53
    Activations Density 0.001%

    No Known Activations