© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252823
    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_56_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
     could
    0.42
    會
    0.41
     would
    0.39
    «.
    0.38
     pourrait
    0.38
     should
    0.38
     όταν
    0.37
     shouldn
    0.37
     WOULD
    0.37
    )$\\
    0.37
    POSITIVE LOGITS
     automatisch
    0.40
    PSW
    0.40
     automático
    0.39
     mutual
    0.38
     automática
    0.38
    Automatically
    0.37
    automatic
    0.36
     automaty
    0.36
    arse
    0.36
    automat
    0.35
    Activations Density 0.000%

    No Known Activations