© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204917
    Prev
    Next
    INDEX
    Explanations

    equal to

    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_25_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
    vertine
    0.42
    conscious
    0.40
    buckets
    0.40
    styled
    0.38
    strong
    0.37
     Κ
    0.37
    क्रम
    0.37
     Changes
    0.36
     ٹرسٹ
    0.36
    illian
    0.36
    POSITIVE LOGITS
     duct
    0.50
     pér
    0.45
     വല
    0.40
     oven
    0.40
    दछ
    0.40
     syslog
    0.39
     marginRight
    0.39
     Czechoslovak
    0.39
    丏
    0.39
     cousin
    0.38
    Activations Density 0.002%

    No Known Activations