© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33617
    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_7_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
    后再
    0.50
    ဣ
    0.48
    л
    0.46
    nThe
    0.44
    的表现
    0.44
    だけでも
    0.44
     seated
    0.43
     leisurely
    0.43
    詣
    0.43
     dominating
    0.42
    POSITIVE LOGITS
    Dieses
    0.71
    HomeScreen
    0.61
    cyclopent
    0.59
    Butyl
    0.58
     पारिवार
    0.56
     secteurs
    0.55
     subpopulations
    0.55
    Meier
    0.54
    vap
    0.53
    Installer
    0.53
    Activations Density 0.000%

    No Known Activations