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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195532
    Prev
    Next
    INDEX
    Explanations

    question 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_26_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
    பிலோ
    0.42
    怿
    0.39
    ებისა
    0.37
    śmy
    0.36
    ರುವುದ
    0.36
    oppositions
    0.36
    レース
    0.36
    ᖏ
    0.36
    恈
    0.35
    部の
    0.35
    POSITIVE LOGITS
    وكب
    0.43
     rectangle
    0.40
     тепло
    0.40
     есть
    0.39
     bilgi
    0.39
     Here
    0.38
     lembrar
    0.38
    "?:
    0.37
     lahat
    0.37
     দক্ষিণে
    0.37
    Activations Density 0.012%

    No Known Activations