© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179192
    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_50_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
     Bern
    0.42
    svr
    0.38
    曙
    0.38
     নাক
    0.38
    ried
    0.36
    Bern
    0.36
     Allie
    0.36
    觚
    0.36
    natures
    0.35
    τσ
    0.35
    POSITIVE LOGITS
    𝗎
    0.52
    पीजी
    0.42
    axiom
    0.39
     singled
    0.38
     chal
    0.37
    пу
    0.37
     رولی
    0.36
    ౌ
    0.36
     Arrangement
    0.35
    OU
    0.35
    Activations Density 0.000%

    No Known Activations