© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164166
    Prev
    Next
    INDEX
    Explanations

    description

    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_13_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
    眼神
    0.49
     misplaced
    0.45
     week
    0.45
     tread
    0.44
     treads
    0.44
     canisters
    0.43
    ()->
    0.42
     array
    0.41
     import
    0.41
     exist
    0.40
    POSITIVE LOGITS
    isimple
    0.56
     عزیز
    0.55
    舩
    0.54
     Каждый
    0.53
    یو
    0.52
    Methylsulfanyl
    0.52
    ithmetic
    0.50
     プラ
    0.50
    ısı
    0.50
     principalColumn
    0.50
    Activations Density 0.000%

    No Known Activations