© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198401
    Prev
    Next
    INDEX
    Explanations

    hindi auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    ťaž
    0.48
     rétréci
    0.47
    还会
    0.47
    റിൽ
    0.46
    Ꮏ
    0.46
    ålet
    0.46
     মেশিন
    0.46
    क्‍
    0.46
     Расійскай
    0.46
    ㎚
    0.45
    POSITIVE LOGITS
     dev
    0.46
     ,
    0.42
     cr
    0.42
     spec
    0.40
     \
    0.38
     complement
    0.38
    0.38
    _
    0.37
     __
    0.37
     studio
    0.35
    Activations Density 0.003%

    No Known Activations