© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27283
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax

    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_40_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
    ኽ
    0.42
    DOCKED
    0.41
     করিত
    0.38
     pě
    0.38
     alkene
    0.37
    ˦
    0.36
     റിപ്പോ
    0.36
     தயாரிக்க
    0.36
     ریکارڈ
    0.36
    㖘
    0.36
    POSITIVE LOGITS
    LAY
    0.39
    Segments
    0.37
    Selection
    0.37
    QUI
    0.36
    |_{\
    0.35
    segments
    0.35
     segments
    0.35
     Selection
    0.35
    LET
    0.34
    _/
    0.34
    Activations Density 0.000%

    No Known Activations