© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24133
    Prev
    Next
    INDEX
    Explanations

    GPU features

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     hand
    2.16
     Hand
    1.76
    手
    1.75
    Hand
    1.71
    hand
    1.68
     HAND
    1.33
    HAND
    1.20
     دست
    1.19
     हैंड
    1.19
    손
    1.18
    POSITIVE LOGITS
     GD
    0.76
    GD
    0.70
     ray
    0.60
     GDR
    0.49
     Ray
    0.48
    ray
    0.47
    Ray
    0.46
     Turing
    0.45
     dedicated
    0.43
     rays
    0.43
    Activations Density 0.220%

    No Known Activations