© 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. 208262
    Prev
    Next
    INDEX
    Explanations

    events and celebrations

    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
     disasters
    0.42
     பின்
    0.41
     storms
    0.40
     Yearly
    0.38
     whatsoever
    0.38
    gek
    0.36
    *\*
    0.36
     कदमों
    0.35
    ᑉ
    0.35
    時代の
    0.35
    POSITIVE LOGITS
     Sard
    0.43
     কা
    0.38
     veloce
    0.37
     δύο
    0.37
    莧
    0.37
    ε
    0.36
     sard
    0.36
     পরিমাণ
    0.36
     ενη
    0.36
    ξ
    0.35
    Activations Density 0.000%

    No Known Activations