© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7062
    Prev
    Next
    INDEX
    Explanations

    this is where

    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_39_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
     extremadamente
    0.35
     Extremely
    0.34
     అత్య
    0.34
     ----->
    0.31
    isser
    0.31
     unmistakable
    0.31
     unmist
    0.31
     தேர்
    0.30
    .–
    0.30
     archiving
    0.29
    POSITIVE LOGITS
    っいて
    0.36
    ≤</
    0.34
    চ্ছিলেন
    0.33
     helpful
    0.33
     उपयोगी
    0.32
     좋아요
    0.32
     सौ
    0.31
     partecipanti
    0.31
    োনা
    0.31
     ಉಪಯೋಗ
    0.31
    Activations Density 0.224%

    No Known Activations