© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146357
    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_18_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
    ini
    0.50
    9
    0.49
    берг
    0.48
    ix
    0.48
    irá
    0.48
    adau
    0.47
    akar
    0.47
    ियस
    0.47
    akra
    0.47
    imi
    0.46
    POSITIVE LOGITS
    こ
    0.56
    も
    0.49
    お
    0.47
    バー
    0.47
     subsistence
    0.47
    🦈
    0.47
    ரண
    0.46
    我们
    0.46
    ใน
    0.46
    不安
    0.46
    Activations Density 0.000%

    No Known Activations