© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201236
    Prev
    Next
    INDEX
    Explanations

    CircleCI CI/CD pipelines

    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_12_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
    biggr
    0.37
     واپس
    0.34
    賽
    0.34
    ち
    0.34
    跑
    0.33
     hre
    0.32
     ，
    0.32
    anlı
    0.32
     tiến
    0.31
    我
    0.31
    POSITIVE LOGITS
     ITV
    0.35
     RAT
    0.35
    QUID
    0.35
     Anticip
    0.35
     QP
    0.34
     Rod
    0.34
     grud
    0.33
     Pesach
    0.33
     Fisk
    0.33
    饉
    0.33
    Activations Density 0.000%

    No Known Activations