© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8852
    Prev
    Next
    INDEX
    Explanations

    theories, conjectures, hypotheses, guesses

    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_13_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
    㓈
    0.46
     Yue
    0.41
     Ευ
    0.39
    ngày
    0.39
     Happy
    0.38
    ská
    0.38
    zhen
    0.37
     จด
    0.37
    ｌ
    0.37
     Menge
    0.37
    POSITIVE LOGITS
     conjectures
    0.52
     guessed
    0.49
     guesses
    0.48
     surm
    0.48
    ک
    0.47
     extrapol
    0.44
     theories
    0.43
     conjecture
    0.42
     предполага
    0.41
     guess
    0.40
    Activations Density 0.106%

    No Known Activations