© 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. 206120
    Prev
    Next
    INDEX
    Explanations

    Cast

    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
     cand
    0.49
    helle
    0.41
    cand
    0.41
     Th
    0.38
     Suga
    0.37
    骢
    0.37
     circus
    0.36
     Grat
    0.36
    cane
    0.35
     statistics
    0.35
    POSITIVE LOGITS
    Iron
    0.86
     Iron
    0.85
     iron
    0.84
    ের
    0.82
     IRON
    0.81
    铁
    0.80
    ی
    0.80
    IRON
    0.77
    s
    0.76
     철
    0.75
    Activations Density 0.000%

    No Known Activations