© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13173
    Prev
    Next
    INDEX
    Explanations

    terms of use/agreement

    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_40_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
    叩
    0.26
     mak
    0.25
     nextline
    0.25
     Protection
    0.24
     तलैया
    0.24
     duc
    0.24
     Cruz
    0.23
     Et
    0.23
     llam
    0.23
     confluence
    0.23
    POSITIVE LOGITS
    规模
    0.25
    ⏩
    0.23
    🈶
    0.22
    Pin
    0.22
    менту
    0.22
    elab
    0.22
    quées
    0.22
    Visitors
    0.22
    ណា
    0.22
    getID
    0.22
    Activations Density 0.020%

    No Known Activations