© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46014
    Prev
    Next
    INDEX
    Explanations

    derogatory nickname

    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_13_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
     Q
    0.55
    <0x8A>
    0.54
     Ia
    0.51
     Iowa
    0.50
     faible
    0.50
     QI
    0.50
     sup
    0.49
     شك
    0.49
     KISS
    0.49
     отмети
    0.49
    POSITIVE LOGITS
    Optimizer
    0.61
    (“
    0.57
    >+</
    0.56
    ل
    0.56
     نماز
    0.55
    чен
    0.54
    з
    0.54
    بعد
    0.53
    מ
    0.53
    टक
    0.53
    Activations Density 0.000%

    No Known Activations