© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39047
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_57_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
    rakes
    0.38
    irteenth
    0.36
    scopic
    0.36
    톨
    0.35
    marshall
    0.34
    Coach
    0.34
    bras
    0.33
    녀
    0.33
    ാനാ
    0.33
    맣
    0.33
    POSITIVE LOGITS
    ަކ
    0.41
     câte
    0.39
     roja
    0.38
     Workshops
    0.37
    واں
    0.36
     Polygon
    0.35
     등의
    0.35
     появи
    0.35
     cried
    0.34
    ലെ
    0.34
    Activations Density 0.193%

    No Known Activations