© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34574
    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_3_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
    কার
    0.63
    ક
    0.63
    वर
    0.62
     বন্ধুদের
    0.62
    اں
    0.60
     solutes
    0.59
    ला
    0.59
    者
    0.58
    en
    0.58
     présentent
    0.58
    POSITIVE LOGITS
     by
    0.75
     on
    0.65
     to
    0.63
    yd
    0.60
     B
    0.59
     at
    0.59
    ן
    0.59
    pository
    0.59
    UtcNow
    0.59
    law
    0.57
    Activations Density 0.000%

    No Known Activations