© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    angular component

    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_39_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
     jumping
    0.35
    豕
    0.35
    hopping
    0.34
    획
    0.34
    joining
    0.33
    悳
    0.33
    Geme
    0.33
     HOP
    0.33
     निघ
    0.33
    स
    0.33
    POSITIVE LOGITS
     fname
    0.36
    slateg
    0.35
    フォト
    0.34
    лым
    0.33
     regulators
    0.32
    넴
    0.32
     unregulated
    0.32
    𒈨
    0.32
    蟀
    0.31
    )';
    0.31
    Activations Density 0.006%

    No Known Activations