© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31520
    Prev
    Next
    INDEX
    Explanations

    research papers

    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_50_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
     wb
    0.40
     करवाए
    0.40
    𝗸
    0.37
     tans
    0.36
    kinder
    0.36
    ക്
    0.36
    効
    0.36
     WB
    0.35
     kary
    0.35
    珺
    0.35
    POSITIVE LOGITS
    raš
    0.43
    duire
    0.43
    rais
    0.42
     आराम
    0.41
    chuk
    0.41
    An
    0.40
    рақ
    0.40
     ഡ്ര
    0.39
    ්ර
    0.38
     An
    0.37
    Activations Density 0.000%

    No Known Activations