© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34918
    Prev
    Next
    INDEX
    Explanations

    The Secret Doctrine

    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_31_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
    йс
    0.41
     ContentView
    0.40
     सोड
    0.40
    ус
    0.39
     অন্তর্
    0.39
     ਵੱ
    0.38
    ","#
    0.38
    Ᏺ
    0.38
     bedding
    0.37
    cellcolor
    0.36
    POSITIVE LOGITS
     problematic
    0.38
    SHUNT
    0.38
    Remember
    0.38
     enth
    0.38
     Account
    0.36
     John
    0.36
     favored
    0.35
     Preferred
    0.35
    shunt
    0.35
     preferred
    0.35
    Activations Density 0.000%

    No Known Activations