© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117323
    Prev
    Next
    INDEX
    Explanations

    DAN, DI, STAN, AIM, BOT personas

    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_27_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
    aggregate
    0.37
     aggregate
    0.33
    Baby
    0.30
    деш
    0.30
    дать
    0.30
    imps
    0.29
    ❢
    0.29
     aggregating
    0.29
     Aggregate
    0.29
    atomic
    0.29
    POSITIVE LOGITS
     diferenças
    0.39
     तय
    0.35
     gostaria
    0.33
     específicos
    0.33
     perbedaan
    0.33
     型
    0.32
     meningkatkan
    0.32
    uminação
    0.31
     rectify
    0.31
     quisiera
    0.31
    Activations Density 0.008%

    No Known Activations