© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175238
    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_24_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
    ktCap
    0.41
    ిత
    0.40
    壹章
    0.40
     "[
    0.39
    дары
    0.38
    structed
    0.37
     military
    0.36
    ्युनिकेशन
    0.36
    ải
    0.36
    ىلى
    0.36
    POSITIVE LOGITS
    翅
    0.48
     cominc
    0.44
    vej
    0.41
    ambiente
    0.40
     underpin
    0.39
     Enables
    0.38
     są
    0.38
    lbrakk
    0.38
     soit
    0.37
    fund
    0.37
    Activations Density 0.000%

    No Known Activations