© 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. 59164
    Prev
    Next
    INDEX
    Explanations

    words and expressions

    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
     ون
    0.40
     ଅ
    0.39
     पीसीएस
    0.38
     ORIGINAL
    0.38
    𒄷
    0.37
     두고
    0.37
    注意的是
    0.37
     (_)
    0.36
     dago
    0.35
    㑼
    0.35
    POSITIVE LOGITS
    words
    0.57
     Worte
    0.43
     words
    0.41
    Factors
    0.39
    Words
    0.39
    beliefs
    0.39
    expressed
    0.39
    ෙ
    0.38
    ทุกคน
    0.38
    differ
    0.38
    Activations Density 0.000%

    No Known Activations