© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136734
    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_12_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
     expulsion
    0.58
     expuls
    0.58
     expelled
    0.58
    ox
    0.57
     expel
    0.56
    <0x80>
    0.55
    ent
    0.54
     exuber
    0.54
    Management
    0.53
     quinquina
    0.52
    POSITIVE LOGITS
     Leach
    0.63
     ಪ್ರತ
    0.56
    ﮯ
    0.55
     Beard
    0.52
    су
    0.52
    ма
    0.50
    ల్‌
    0.50
     Ey
    0.50
     Leigh
    0.50
    м
    0.50
    Activations Density 0.000%

    No Known Activations