© 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. 204598
    Prev
    Next
    INDEX
    Explanations

    punctuation or non-English words

    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
     grants
    0.43
     judgements
    0.40
     لي
    0.39
     judgement
    0.38
     deletes
    0.38
     blames
    0.38
     ليصل
    0.38
    ็
    0.37
     وس
    0.36
     उद्देश्य
    0.36
    POSITIVE LOGITS
     যেগুলো
    0.39
     cuales
    0.37
    langs
    0.37
     lesquelles
    0.37
     करूं
    0.36
     Austria
    0.36
     lesquels
    0.36
    тары
    0.36
    它的
    0.36
     allgeme
    0.36
    Activations Density 0.001%

    No Known Activations