© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203939
    Prev
    Next
    INDEX
    Explanations

    ISO 8601 timestamp format

    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_37_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
    两天
    0.48
     Hours
    0.44
    午
    0.43
     DAYS
    0.41
     afternoon
    0.40
    ivalence
    0.39
    Days
    0.38
     HOURS
    0.38
     Days
    0.38
     दोपहर
    0.38
    POSITIVE LOGITS
     period
    0.47
    時期
    0.46
     celebrating
    0.44
     commemorating
    0.43
     कार्यरत
    0.40
     #(
    0.39
     Epoch
    0.39
    period
    0.39
    zov
    0.39
     peak
    0.38
    Activations Density 0.001%

    No Known Activations