© 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
    2. Gemma-3-27B-IT
    3. 24-GEMMASCOPE-2-TRANSCODER-262K
    4. 180613
    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
    quisition
    0.41
    кә
    0.38
    چا
    0.38
     planis
    0.37
    ෛ
    0.37
     volley
    0.36
     rains
    0.36
     доби
    0.36
     caregiver
    0.36
     flavor
    0.35
    POSITIVE LOGITS
     Decl
    0.36
     projective
    0.36
    ຯ
    0.35
    ခဲ့
    0.35
     ವಿರುದ್ಧ
    0.35
     drunkenness
    0.34
     odpowiedzial
    0.34
    jobNumber
    0.34
     EJ
    0.34
     UI
    0.33
    Activations Density 0.000%

    No Known Activations