© 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. 3480
    Prev
    Next
    INDEX
    Explanations

    css properties

    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
     supersymmetric
    0.22
     nonparametric
    0.22
    ximation
    0.21
    劝
    0.21
    嗡
    0.21
    hydraulic
    0.20
    chern
    0.20
    inductive
    0.20
     Collegiate
    0.20
     Correa
    0.20
    POSITIVE LOGITS
     Fet
    0.22
    Об
    0.21
    鈳
    0.21
    Ernest
    0.20
    Kenneth
    0.20
     haul
    0.20
    গর্
    0.20
    兌
    0.19
     slee
    0.19
     fet
    0.19
    Activations Density 0.021%

    No Known Activations