© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21044
    Prev
    Next
    INDEX
    Explanations

    AI capabilities model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     «
    0.45
     (
    0.41
    0.39
     modern
    0.36
    sex
    0.36
    ...
    0.36
     further
    0.36
    able
    0.36
     [
    0.35
    m
    0.35
    POSITIVE LOGITS
    躓
    0.43
     मिमी
    0.40
     ಇದೆ
    0.39
     ৃ
    0.39
    𝗥
    0.38
    <unused458>
    0.37
    <unused1059>
    0.37
    eonium
    0.37
     basilaires
    0.37
     pérd
    0.37
    Activations Density 0.281%

    No Known Activations