© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18707
    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_40_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
    Ử
    0.42
     ideology
    0.40
     Sew
    0.39
     Андроид
    0.38
    揾
    0.38
     Disponible
    0.37
     identifier
    0.36
    Sew
    0.36
     nominal
    0.35
     relations
    0.35
    POSITIVE LOGITS
    <0xA4>
    0.45
     בלי
    0.41
     weep
    0.40
    ilta
    0.39
    uyan
    0.38
     الخط
    0.38
    öss
    0.38
    知り
    0.38
    nesses
    0.38
    De
    0.37
    Activations Density 0.000%

    No Known Activations