© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216145
    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_31_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
     pronounced
    0.41
     ध्व
    0.37
    šnje
    0.37
    מר
    0.37
    醺
    0.36
     uttered
    0.35
    tikz
    0.35
     Beginning
    0.35
     alright
    0.35
     symmetries
    0.35
    POSITIVE LOGITS
    Runnable
    0.41
    iec
    0.40
     PCS
    0.39
    igueur
    0.39
    䛊
    0.38
    なくて
    0.38
    㯎
    0.38
    貴重
    0.38
    íos
    0.37
    IVOS
    0.37
    Activations Density 0.000%

    No Known Activations