© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108809
    Prev
    Next
    INDEX
    Explanations

    Rites, mites, kites

    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_2_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
    ل
    2.08
    ન
    1.59
    ing
    1.56
    ر
    1.47
    ל
    1.39
    nd
    1.36
    ra
    1.34
    л
    1.33
     by
    1.23
    r
    1.20
    POSITIVE LOGITS
    <0x80>
    1.26
    ↵
    1.12
    ี
    1.05
     zwią
    0.99
    ́n
    0.98
     rekao
    0.97
     আরো
    0.96
    ิ
    0.94
    ujú
    0.93
    の問題
    0.92
    Activations Density 0.001%

    No Known Activations