© 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. 93263
    Prev
    Next
    INDEX
    Explanations

    Hindi auxiliary 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_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
    把
    0.59
     का
    0.51
     把
    0.48
    行う
    0.47
    या
    0.46
    ের
    0.46
     ya
    0.45
    s
    0.44
    行
    0.44
    geç
    0.43
    POSITIVE LOGITS
     решил
    0.59
     сделал
    0.59
     заявил
    0.58
     понял
    0.58
     получил
    0.57
     взял
    0.57
     miał
    0.55
    ள்ளார்
    0.54
     தெரிவித்தார்
    0.54
     начал
    0.53
    Activations Density 0.000%

    No Known Activations