© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123061
    Prev
    Next
    INDEX
    Explanations

    ImGui syntax

    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_37_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
     Bore
    0.42
     bore
    0.42
    bore
    0.41
    澜
    0.41
    ર્મ
    0.41
    열
    0.36
     ис
    0.36
    멜
    0.36
    )_{
    0.35
     Austral
    0.35
    POSITIVE LOGITS
     Im
    0.42
    Referencias
    0.42
     Dear
    0.40
     Item
    0.39
    ertas
    0.39
     Obed
    0.39
    Im
    0.38
    inars
    0.37
     Icon
    0.37
    ఙ
    0.37
    Activations Density 0.002%

    No Known Activations