© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51374
    Prev
    Next
    INDEX
    Explanations

    honest feedback and reviews

    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_30_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
    耠
    0.40
     but
    0.39
     religiously
    0.36
    xcol
    0.36
     кос
    0.35
     conveniently
    0.35
    하지만
    0.34
    OLA
    0.34
    ola
    0.34
    ҳ
    0.34
    POSITIVE LOGITS
     ciągu
    0.39
     cinco
    0.38
    迺
    0.38
     lendemain
    0.37
     stdin
    0.37
     خمسه
    0.36
    คือ
    0.36
    صميم
    0.36
     टै
    0.35
     nueve
    0.35
    Activations Density 0.000%

    No Known Activations