© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63572
    Prev
    Next
    INDEX
    Explanations

    Hindi verbs

    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_59_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
     되
    1.02
    わかり
    0.73
    分かり
    0.71
     ol
    0.52
    ವ
    0.46
    始まり
    0.45
    まり
    0.44
     విడు
    0.43
     lle
    0.43
    ై
    0.41
    POSITIVE LOGITS
     बने
    1.34
     लगे
    1.32
     मिले
    1.30
     रहे
    1.26
     आए
    1.22
     पड़े
    1.13
     आये
    1.12
     पहुंचे
    1.09
     لگے
    1.05
     निकले
    1.04
    Activations Density 0.000%

    No Known Activations