© 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. 199665
    Prev
    Next
    INDEX
    Explanations

    def

    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
    Not in Any Lists

    No Comments

    Negative Logits
     रिश्तों
    0.39
    科技有限公司
    0.38
    Baked
    0.38
    瘓
    0.38
    ✎
    0.37
     सर्व
    0.36
     Respiratory
    0.36
     превра
    0.36
     AcOEt
    0.36
     BOUND
    0.35
    POSITIVE LOGITS
    ը
    0.40
    zie
    0.39
    становка
    0.38
    erte
    0.37
     alias
    0.35
    erca
    0.34
    ennis
    0.34
     wiel
    0.33
    elie
    0.33
    block
    0.33
    Activations Density 0.002%

    No Known Activations