© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10981
    Prev
    Next
    INDEX
    Explanations

    Unicode characters

    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_40_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
    Proguard
    0.39
    ‮
    0.36
     ঘটে
    0.35
    ['
    0.35
    Profiles
    0.35
    帘
    0.35
     bur
    0.35
    뚝
    0.35
    ファイル
    0.34
     রাখ
    0.34
    POSITIVE LOGITS
     Assigned
    0.46
    assigned
    0.44
     asign
    0.44
     assigned
    0.43
     Plane
    0.43
    oł
    0.41
     assign
    0.41
     assigns
    0.41
     assegn
    0.40
    Assign
    0.40
    Activations Density 0.004%

    No Known Activations