© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200060
    Prev
    Next
    INDEX
    Explanations

    score after a number

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     암
    0.42
    暗
    0.40
     मन
    0.38
     Advice
    0.38
     ам
    0.36
     sx
    0.36
     Encryption
    0.36
     측정
    0.35
    七
    0.35
     хо
    0.35
    POSITIVE LOGITS
    Troy
    0.42
    inä
    0.41
    beforeend
    0.40
     generically
    0.40
    éry
    0.39
    शिता
    0.39
     GEN
    0.38
    Marvel
    0.38
    alista
    0.38
    Bet
    0.38
    Activations Density 0.000%

    No Known Activations