© 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. 208917
    Prev
    Next
    INDEX
    Explanations

    filling blanks or masked 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
    疾患
    0.42
    えている
    0.41
     množství
    0.38
    ဣ
    0.38
     सक्सेना
    0.38
    лық
    0.36
     과정
    0.36
     कोश
    0.36
     carbohyd
    0.36
    VK
    0.36
    POSITIVE LOGITS
     Continental
    0.39
     different
    0.37
    쯔
    0.36
    ра
    0.35
     Kupp
    0.35
     Different
    0.35
     Cheng
    0.35
     Ku
    0.34
    arre
    0.34
     FIG
    0.34
    Activations Density 0.003%

    No Known Activations