© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138712
    Prev
    Next
    INDEX
    Explanations

    string stream operator

    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
    er
    0.60
     Lombok
    0.60
     arranged
    0.59
     spoke
    0.59
     greeted
    0.57
     laying
    0.57
     accentuated
    0.57
    ă
    0.56
     Jakarta
    0.55
    在
    0.55
    POSITIVE LOGITS
    ）【
    0.54
    ನೇ
    0.52
    صاص
    0.49
     نیند
    0.49
    armament
    0.48
    ઓ
    0.47
    邈
    0.46
    SizeType
    0.45
    SETS
    0.45
    causing
    0.44
    Activations Density 0.001%

    No Known Activations