© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106564
    Prev
    Next
    INDEX
    Explanations

    discussion

    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_1_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
    2
    1.47
    ت
    1.45
     legitim
    1.28
    s
    1.19
     be
    1.16
    ft
    1.15
    是
    1.13
    т
    1.13
    ب
    1.10
     promover
    1.07
    POSITIVE LOGITS
    an
    0.95
    다라고
    0.91
    다
    0.84
    ously
    0.83
    으며
    0.82
    adillo
    0.80
     foothold
    0.79
    anlı
    0.76
    inafter
    0.75
    وڑا
    0.74
    Activations Density 0.002%

    No Known Activations