© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7257
    Prev
    Next
    INDEX
    Explanations

    limit notation

    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_39_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
    hers
    0.39
     hechas
    0.39
     tark
    0.37
    veys
    0.37
     speck
    0.35
    vané
    0.35
    樽
    0.34
     serializers
    0.34
    aries
    0.34
    잊
    0.33
    POSITIVE LOGITS
    expression
    0.37
    Prior
    0.37
    ალური
    0.36
    Vita
    0.34
     Schm
    0.34
     Kne
    0.34
     ptr
    0.32
     bp
    0.31
    Fields
    0.31
     drugs
    0.31
    Activations Density 0.008%

    No Known Activations