© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235292
    Prev
    Next
    INDEX
    Explanations

    image URLs

    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
     disordered
    0.43
     !***
    0.41
     "*****
    0.40
     izvr
    0.40
    ᙱ
    0.40
     ضروری
    0.39
    ‍♂
    0.39
     Prib
    0.39
     edgecolor
    0.38
     Elytres
    0.38
    POSITIVE LOGITS
    Party
    0.43
    陳
    0.43
     Dec
    0.42
    Dec
    0.41
    Chen
    0.41
    IMG
    0.41
    陈
    0.40
    구를
    0.39
    Sy
    0.39
    Cal
    0.38
    Activations Density 0.001%

    No Known Activations