© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215911
    Prev
    Next
    INDEX
    Explanations

    RCE, CE, DNF, vulnerability

    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    '
    1.91
     as
    1.23
    വ
    1.20
    1
    1.19
    也
    1.18
     a
    1.16
     by
    1.13
    _
    1.11
    ’
    1.10
    的
    1.10
    POSITIVE LOGITS
    <0x0D>
    1.38
    ین
    1.27
    ੇ
    1.20
    </h3>
    1.13
    ری
    1.05
     فونی
    1.02
    </h1>
    1.01
     holomorphic
    0.99
    ریس
    0.98
     ardent
    0.98
    Activations Density 0.000%

    No Known Activations