© 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. 79219
    Prev
    Next
    INDEX
    Explanations

    SQL insert statements and python files

    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
     declines
    0.39
     ?”
    0.39
    ㄚ
    0.39
    BOTH
    0.38
     arrowhead
    0.38
     liberty
    0.37
     blacks
    0.37
     elimin
    0.37
     слабы
    0.37
    DIRECTION
    0.36
    POSITIVE LOGITS
     ವ್ಯ
    0.48
    subj
    0.42
     Cour
    0.39
    ኑ
    0.39
     ক্যাম্প
    0.39
     partition
    0.38
     student
    0.38
     Allocation
    0.38
     přev
    0.38
     Kors
    0.37
    Activations Density 0.003%

    No Known Activations