© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92810
    Prev
    Next
    INDEX
    Explanations

    **

    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_60_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
    要
    0.42
     要
    0.40
    leau
    0.39
    Want
    0.39
    מש
    0.39
     sende
    0.38
     Dez
    0.38
    )$\
    0.37
     מש
    0.37
    pues
    0.36
    POSITIVE LOGITS
     Th
    0.50
     Ked
    0.44
     Bed
    0.43
     ked
    0.43
     मिळ
    0.42
     Mala
    0.42
    Th
    0.41
     Ман
    0.41
     Thal
    0.41
    ंचे
    0.40
    Activations Density 0.000%

    No Known Activations