© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11339
    Prev
    Next
    INDEX
    Explanations

    bold, italic, font, style

    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_13_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
     Shots
    0.43
    畛
    0.43
     ilg
    0.41
     Cameras
    0.41
    assisted
    0.40
    कविता
    0.40
    vasser
    0.39
    ACCT
    0.39
     कब्
    0.39
     Course
    0.38
    POSITIVE LOGITS
    s
    0.50
    ˀ
    0.44
    يس
    0.42
    Е
    0.42
    ː
    0.40
    ни
    0.39
     вста
    0.39
     fierce
    0.39
     admiring
    0.39
     dont
    0.38
    Activations Density 0.095%

    No Known Activations