© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252388
    Prev
    Next
    INDEX
    Explanations

    Alphon

    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
    赢
    0.41
     recomp
    0.38
     usw
    0.36
    贏
    0.35
    iali
    0.35
    geoip
    0.35
    ymal
    0.34
     ganar
    0.34
    FormParams
    0.34
    拇
    0.34
    POSITIVE LOGITS
     Print
    0.70
     print
    0.68
    print
    0.61
    Print
    0.49
    eer
    0.45
     Case
    0.44
     \"
    0.43
    much
    0.42
     Much
    0.42
    եր
    0.41
    Activations Density 0.000%

    No Known Activations