© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193077
    Prev
    Next
    INDEX
    Explanations

    our world

    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_4_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
    ва
    0.76
    hole
    0.70
     çıkar
    0.66
     són
    0.66
    ﻢ
    0.63
    המ
    0.61
     PAYMENT
    0.60
    ջ
    0.60
    phone
    0.59
    ш
    0.59
    POSITIVE LOGITS
    n
    0.88
    ت
    0.83
    y
    0.78
    ات
    0.76
    b
    0.75
    s
    0.72
    is
    0.72
    yah
    0.72
    m
    0.70
    cendo
    0.70
    Activations Density 0.001%

    No Known Activations