© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181045
    Prev
    Next
    INDEX
    Explanations

    tell me what to ask

    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_24_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
     surfer
    0.38
     style
    0.38
     रहे
    0.34
    ადი
    0.33
     f
    0.33
     observers
    0.33
    फिर
    0.32
     quadratic
    0.32
     sty
    0.32
    欢迎
    0.32
    POSITIVE LOGITS
     অর্ধেক
    0.37
     mão
    0.37
    anthemum
    0.37
     Sprache
    0.36
     govor
    0.36
    쭐
    0.36
     güzel
    0.35
     vuel
    0.35
    chaos
    0.34
    ravés
    0.34
    Activations Density 0.000%

    No Known Activations