© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194435
    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_27_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
     //
    0.33
     Vys
    0.33
     permanec
    0.32
     активность
    0.32
     VT
    0.31
     permanecer
    0.30
    த்திலேயே
    0.30
     aktivnosti
    0.30
     ////
    0.30
     سوری
    0.30
    POSITIVE LOGITS
    Renk
    0.30
     విలువ
    0.30
     compuls
    0.30
    Dip
    0.30
     gill
    0.29
    値
    0.29
    Did
    0.29
     daw
    0.29
    Nationality
    0.29
    Frequently
    0.29
    Activations Density 0.000%

    No Known Activations