© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50292
    Prev
    Next
    INDEX
    Explanations

    on + 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_10_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
    т
    0.59
    ل
    0.51
    on
    0.47
    尔
    0.46
    ों
    0.45
    at
    0.45
    к
    0.44
    л
    0.42
     оно
    0.42
     рядом
    0.41
    POSITIVE LOGITS
    な
    0.50
    まさに
    0.49
    ovima
    0.46
    kadang
    0.44
     but
    0.44
    že
    0.42
     entraî
    0.42
     for
    0.42
    gives
    0.41
    ד
    0.41
    Activations Density 0.011%

    No Known Activations