© 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. 249861
    Prev
    Next
    INDEX
    Explanations

    inference

    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
    推
    2.47
     推
    1.86
     pushing
    1.77
     push
    1.72
     pushed
    1.72
     pushes
    1.72
    Push
    1.70
     Push
    1.67
     추
    1.56
    push
    1.55
    POSITIVE LOGITS
    inf
    0.41
     Ix
    0.38
     मै
    0.36
    lings
    0.35
    ﻁ
    0.35
     Inf
    0.35
     Goddess
    0.35
    roep
    0.35
     ول
    0.34
     infinitely
    0.34
    Activations Density 0.005%

    No Known Activations