© 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. 17509
    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
    Chair
    0.42
     Countdown
    0.41
     ô
    0.40
    础
    0.38
     Clip
    0.38
    ôs
    0.38
    Organic
    0.37
    礎
    0.37
    Prem
    0.37
    Base
    0.37
    POSITIVE LOGITS
     exter
    0.54
    sequences
    0.52
     exterior
    0.49
     sequences
    0.48
     exteriores
    0.46
     establishing
    0.46
     interiors
    0.44
     Sequences
    0.43
     seq
    0.43
     sequencing
    0.42
    Activations Density 0.011%

    No Known Activations