© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46164
    Prev
    Next
    INDEX
    Explanations

    CanContainContent: true

    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
    -
    0.66
    ology
    0.58
    i
    0.57
    ership
    0.52
    safe
    0.52
    eller
    0.51
    hende
    0.51
    istische
    0.51
    y
    0.50
    works
    0.50
    POSITIVE LOGITS
     Generator
    0.53
    ังสือ
    0.52
     kcal
    0.52
     酒
    0.51
    酒
    0.50
     Language
    0.50
    یں۔
    0.50
     LANGUAGE
    0.49
     sangue
    0.49
     نجي
    0.49
    Activations Density 0.000%

    No Known Activations