© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196015
    Prev
    Next
    INDEX
    Explanations

    Cy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     সী
    0.44
    ાળ
    0.44
    ストラ
    0.42
    聡
    0.42
    ঙ্ক
    0.42
     કાર્
    0.41
     വിശ്വാ
    0.39
    忿
    0.39
    ুদ্ধ
    0.39
    سه
    0.39
    POSITIVE LOGITS
    N
    0.41
    EntityType
    0.39
    šn
    0.37
    Coat
    0.35
     নিল
    0.35
     Niko
    0.35
     N
    0.34
     coat
    0.34
     ہتھیار
    0.34
     ন
    0.34
    Activations Density 0.000%

    No Known Activations