© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154030
    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_23_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
     igreja
    0.52
    的
    0.49
    ⴳ
    0.48
     Geräte
    0.47
     Team
    0.46
    噰
    0.46
    谒
    0.46
    υσ
    0.44
     Remembering
    0.43
    埂
    0.43
    POSITIVE LOGITS
     kitt
    0.48
     elasticity
    0.48
     switched
    0.47
    sigmoid
    0.46
     linearity
    0.46
     त्यौहार
    0.45
    linearity
    0.44
     ridiculed
    0.44
     inclinations
    0.43
     renormalized
    0.43
    Activations Density 0.000%

    No Known Activations