© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258552
    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_22_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
    y
    0.52
    கோ
    0.51
    Об
    0.50
     egip
    0.50
    قي
    0.49
     Tanz
    0.49
     siete
    0.49
    Т
    0.48
    कि
    0.48
     Congo
    0.48
    POSITIVE LOGITS
     тепер
    0.46
     편리
    0.43
     특히
    0.42
     ತಮ್ಮ
    0.42
     현재
    0.41
     অবাধ
    0.40
    abhavena
    0.40
     최대한
    0.40
     vững
    0.39
     위험
    0.39
    Activations Density 0.000%

    No Known Activations