© 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. 178401
    Prev
    Next
    INDEX
    Explanations

    database connection details

    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
    Vision
    0.45
    University
    0.42
     ம
    0.41
    Frames
    0.40
    Dem
    0.39
    ÍN
    0.39
     khởi
    0.39
    рона
    0.38
     வெளிய
    0.37
     ờ
    0.37
    POSITIVE LOGITS
     eventual
    0.38
     bottom
    0.37
     tokom
    0.37
    ierend
    0.37
    abled
    0.37
    illah
    0.37
     habitually
    0.37
     thread
    0.36
     hardened
    0.36
     dokon
    0.36
    Activations Density 0.000%

    No Known Activations