© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252503
    Prev
    Next
    INDEX
    Explanations

    options and conditions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    更
    2.72
     more
    2.27
     更
    2.20
     более
    2.08
     더
    2.05
     lebih
    2.03
     أكثر
    1.98
    更加
    1.98
    更有
    1.95
    더
    1.93
    POSITIVE LOGITS
    uttosto
    0.43
    多了
    0.37
    ниці
    0.36
    akkh
    0.34
    ̩
    0.34
    ప్పు
    0.33
    㓩
    0.33
    plicated
    0.33
    ன்றி
    0.33
    ંભ
    0.33
    Activations Density 0.003%

    No Known Activations