© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 129910
    Prev
    Next
    INDEX
    Explanations

    PRIMARY AUTO

    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
    คู่
    0.38
     potens
    0.38
    谢
    0.36
     togel
    0.36
     období
    0.34
    对
    0.34
     sebelumnya
    0.34
     bł
    0.33
    Curl
    0.32
     previous
    0.32
    POSITIVE LOGITS
     kato
    0.40
    radiation
    0.39
    frau
    0.38
    谥
    0.37
    pham
    0.37
    უნქ
    0.36
     diz
    0.36
    𝗞
    0.36
    mapstruct
    0.36
    horst
    0.36
    Activations Density 0.000%

    No Known Activations