© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143739
    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_0_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
     beak
    0.50
     confronts
    0.47
    शर
    0.46
     Fas
    0.46
     ponies
    0.45
    渴
    0.45
    chacha
    0.45
    ilin
    0.44
     sparsely
    0.44
     bores
    0.44
    POSITIVE LOGITS
    Woman
    0.55
    Inher
    0.53
    Related
    0.52
    Subscriber
    0.52
    ラ
    0.52
    Child
    0.51
    ബ്
    0.50
    uah
    0.49
     Израи
    0.49
     中国
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.