© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252407
    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_56_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
    sman
    0.37
     microsomal
    0.37
    ​—
    0.35
    post
    0.33
    진
    0.33
     posts
    0.33
    साथ
    0.33
    း
    0.32
    posts
    0.32
     taping
    0.32
    POSITIVE LOGITS
    緍
    0.34
    亣
    0.34
    Ire
    0.33
    특별시
    0.33
     =,
    0.33
    ρίζ
    0.33
    䄳
    0.33
    ocsát
    0.32
    REGIUNE
    0.32
    empot
    0.32
    Activations Density 0.000%

    No Known Activations