© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166481
    Prev
    Next
    INDEX
    Explanations

    able to describe

    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_34_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
     corrupción
    0.39
     Explosion
    0.37
     χρώ
    0.37
    𒌷
    0.37
     IRR
    0.37
    negoti
    0.36
     BAH
    0.36
     Number
    0.36
     чисел
    0.36
    と呼ば
    0.35
    POSITIVE LOGITS
    adka
    0.42
    把你
    0.42
     journal
    0.38
    苟
    0.37
    снов
    0.37
     lactation
    0.37
     sheets
    0.36
     verticals
    0.36
     manga
    0.36
     gird
    0.36
    Activations Density 0.001%

    No Known Activations