© 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. 170054
    Prev
    Next
    INDEX
    Explanations

    H

    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
     hinge
    1.53
     hinged
    1.47
     hinges
    1.41
     Hing
    1.26
     hing
    1.21
    hing
    1.13
    铰
    0.91
    Turn
    0.69
    转
    0.64
     转
    0.62
    POSITIVE LOGITS
     H
    1.03
    H
    0.95
     اله
    0.89
     ह
    0.81
     ஹ
    0.71
    Ｈ
    0.69
     एच
    0.67
     হ
    0.67
     הה
    0.66
     ਹ
    0.64
    Activations Density 0.003%

    No Known Activations