© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83719
    Prev
    Next
    INDEX
    Explanations

    shanty

    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_0_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
    1
    1.53
    re
    1.52
    ut
    1.47
    6
    1.42
    ra
    1.40
    Name
    1.36
    8
    1.34
    9
    1.34
    K
    1.33
    4
    1.32
    POSITIVE LOGITS
     at
    1.89
    ร
    1.53
    ر
    1.51
     can
    1.49
    د
    1.49
    ف
    1.45
    ה
    1.35
    ق
    1.30
    ன்
    1.28
    ง
    1.26
    Activations Density 0.000%

    No Known Activations