© 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. 158715
    Prev
    Next
    INDEX
    Explanations

    ever + past participle

    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
    ن
    1.65
    س
    1.52
    ס
    1.48
     is
    1.48
    ال
    1.46
    は
    1.43
    是
    1.39
    ン
    1.38
    ง
    1.29
    г
    1.28
    POSITIVE LOGITS
    u
    1.70
    us
    1.45
    at
    1.19
    y
    1.13
    ed
    1.05
    し
    1.04
    보는
    1.00
    しっかり
    0.99
    k
    0.96
    あり
    0.96
    Activations Density 0.000%

    No Known Activations