© 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. 214428
    Prev
    Next
    INDEX
    Explanations

    anime studios

    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
     Fad
    0.49
     Merck
    0.43
     Mexican
    0.42
     Prism
    0.41
     Fest
    0.41
     Ann
    0.40
     Lup
    0.40
    卢
    0.40
     Equipped
    0.39
     Ani
    0.39
    POSITIVE LOGITS
    debugElement
    0.41
     zer
    0.40
     আসিয়া
    0.40
    Douglas
    0.38
    convergence
    0.38
    ığım
    0.37
    remmo
    0.37
    ığınız
    0.36
    dinner
    0.36
    ﻊ
    0.36
    Activations Density 0.000%

    No Known Activations