© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78409
    Prev
    Next
    INDEX
    Explanations

    example output

    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_29_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
    িয়ায়
    0.39
     residual
    0.38
     unobstructed
    0.36
     breath
    0.36
    鍍
    0.36
     tides
    0.35
    UIActions
    0.35
    uix
    0.35
     imping
    0.34
    钤
    0.34
    POSITIVE LOGITS
    แล้ว
    0.44
     asli
    0.38
     until
    0.37
     Da
    0.37
    σωπ
    0.36
    യിരുന്നു
    0.36
    ಂತ
    0.36
    พัน
    0.36
     للط
    0.36
     معیار
    0.35
    Activations Density 0.001%

    No Known Activations