© 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. 204397
    Prev
    Next
    INDEX
    Explanations

    node_modules

    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
     অধিদপ্তর
    0.43
    𝙽
    0.42
     ಇದೆ
    0.41
    Ń
    0.39
     നമഃ
    0.38
     അല്ല
    0.38
    চলিত
    0.38
    ವಿಧ
    0.37
     অঞ্চলে
    0.36
     подобные
    0.36
    POSITIVE LOGITS
     confortable
    0.40
     comfortable
    0.38
    ஒரு
    0.37
    áveis
    0.36
    再び
    0.36
     comfortably
    0.36
    啸
    0.35
     incl
    0.35
     encara
    0.35
     nje
    0.34
    Activations Density 0.000%

    No Known Activations