© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7443
    Prev
    Next
    INDEX
    Explanations

    Transformer architecture excels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    瀾
    0.38
     accommod
    0.37
    澜
    0.37
    难
    0.37
     dissent
    0.37
     Reed
    0.35
     şidd
    0.35
    含ま
    0.35
    结
    0.35
    Reed
    0.35
    POSITIVE LOGITS
     outperform
    0.46
     Joint
    0.43
    Joint
    0.41
     সার্বভৌম
    0.41
     Germ
    0.40
     outperformed
    0.38
    Zoom
    0.38
     joint
    0.37
    trap
    0.37
    :'],
    0.37
    Activations Density 0.290%

    No Known Activations