© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165162
    Prev
    Next
    INDEX
    Explanations

    居四川

    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_31_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
     Parry
    0.34
     ٹھ
    0.34
    忒
    0.34
     הא
    0.33
     ਟ
    0.32
     promised
    0.32
     partitions
    0.31
     نع
    0.31
    宒
    0.31
     تہ
    0.30
    POSITIVE LOGITS
    गोल
    0.30
    ালন
    0.30
    atak
    0.30
    μεν
    0.29
    영
    0.29
    นอน
    0.29
    მდეგ
    0.29
     MP
    0.28
     resigned
    0.28
    ISON
    0.28
    Activations Density 0.002%

    No Known Activations