© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204984
    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_37_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
    ëm
    0.35
     이미
    0.34
    appell
    0.34
     w
    0.33
    ë
    0.33
    Ë
    0.33
    दर्शक
    0.32
    存
    0.32
     وصول
    0.32
     Poe
    0.32
    POSITIVE LOGITS
     radi
    0.43
     ساي
    0.40
     Kampf
    0.39
     Verantwort
    0.39
     radic
    0.39
    cvec
    0.38
     Paleo
    0.38
     Conn
    0.38
     laboratoires
    0.38
    rparam
    0.37
    Activations Density 0.000%

    No Known Activations