© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88197
    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_23_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
     slip
    0.48
     decouple
    0.48
     stronger
    0.46
    analytic
    0.45
    accuracy
    0.45
     Exist
    0.45
     exists
    0.44
     后
    0.44
     esist
    0.44
    Rec
    0.43
    POSITIVE LOGITS
    屾
    0.47
    生
    0.41
    Тем
    0.39
    胃
    0.39
    Же
    0.39
    лл
    0.38
     Kimberly
    0.38
    ायक
    0.38
    мир
    0.38
     темпера
    0.38
    Activations Density 0.000%

    No Known Activations