© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134134
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    '
    1.52
    is
    1.38
    -
    1.36
    ',
    1.21
    im
    1.20
    ik
    1.20
    </h3>
    1.14
    ide
    1.13
     I
    1.10
    ag
    1.09
    POSITIVE LOGITS
    ي
    1.59
    ع
    1.27
    ת
    1.15
    و
    1.11
    不喜欢
    1.05
     смесь
    1.04
     большой
    1.01
    话
    0.96
    다
    0.96
     ткань
    0.95
    Activations Density 0.000%

    No Known Activations