© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167888
    Prev
    Next
    INDEX
    Explanations

    translation/interpretation

    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
     ver
    0.50
     सटीक
    0.41
     PWMB
    0.38
     con
    0.38
    lasan
    0.38
    合った
    0.38
     राशिफल
    0.37
    𝕨
    0.37
     Ver
    0.36
    報
    0.35
    POSITIVE LOGITS
     adalah
    0.60
     είναι
    0.53
     là
    0.51
     interprets
    0.50
    là
    0.49
     sees
    0.48
     是
    0.47
    是一
    0.47
     interpr
    0.47
    see
    0.46
    Activations Density 0.003%

    No Known Activations