© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5679
    Prev
    Next
    INDEX
    Explanations

    xml version

    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_38_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
     Valent
    0.45
     לת
    0.40
     vesicles
    0.40
     Axes
    0.39
    աղ
    0.39
     coefficients
    0.38
     eu
    0.37
    裵
    0.36
     coefficient
    0.36
     компонен
    0.36
    POSITIVE LOGITS
    startswith
    0.41
    Logo
    0.40
     Scope
    0.40
    logo
    0.39
    Record
    0.39
    aris
    0.39
    header
    0.38
    Scope
    0.38
     Logo
    0.37
    檜
    0.37
    Activations Density 0.001%

    No Known Activations