© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27467
    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_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
    ̻
    0.40
     friction
    0.38
    ocie
    0.38
    ውን
    0.36
     intractable
    0.35
    irds
    0.35
    惨
    0.35
    ંચ
    0.34
     AppException
    0.34
    台
    0.33
    POSITIVE LOGITS
     deferred
    3.03
    Deferred
    2.73
     defer
    2.72
     Deferred
    2.72
    deferred
    2.66
     delayed
    2.50
    defer
    2.44
    Defer
    2.41
     Delayed
    2.34
     postponed
    2.30
    Activations Density 0.152%

    No Known Activations