© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86775
    Prev
    Next
    INDEX
    Explanations

    list

    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_23_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
     inwon
    0.48
     Shooter
    0.43
    ဳ
    0.39
    zeme
    0.38
     tình
    0.36
     షూ
    0.36
    ጅ
    0.36
     międzynarod
    0.35
    iens
    0.35
     shooter
    0.34
    POSITIVE LOGITS
    고
    0.34
    UAL
    0.32
    눈
    0.32
    GONDOR
    0.32
     ecol
    0.31
     وتش
    0.31
     sprinkling
    0.31
     голо
    0.31
     ២
    0.31
    거나
    0.31
    Activations Density 0.012%

    No Known Activations