© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199721
    Prev
    Next
    INDEX
    Explanations

    30-60 seconds

    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_12_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
    م
    0.42
     S
    0.39
    ז
    0.37
    ش
    0.37
    ท
    0.37
    خ
    0.36
     herni
    0.35
     H
    0.34
    ді
    0.34
    ße
    0.34
    POSITIVE LOGITS
    EC
    0.37
     ờ
    0.36
    rá
    0.35
    ем
    0.35
    og
    0.34
     తో
    0.34
    𝒐
    0.34
    c
    0.34
     комнаты
    0.34
    ност
    0.34
    Activations Density 0.001%

    No Known Activations