© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18227
    Prev
    Next
    INDEX
    Explanations

    measure word + noun

    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_34_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
     этой
    0.40
     kinda
    0.39
    шы
    0.39
     (>
    0.38
    шым
    0.38
     unveils
    0.37
     unveiling
    0.37
    ತಾ
    0.36
     einer
    0.36
    Malley
    0.36
    POSITIVE LOGITS
     hó
    0.39
    做好
    0.39
    特殊的
    0.39
    主要的
    0.39
     gjorde
    0.38
    著名的
    0.38
     외
    0.37
    新的
    0.37
     personnalité
    0.37
     Tö
    0.36
    Activations Density 0.006%

    No Known Activations