© 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. 161984
    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
     undeni
    0.35
    પા
    0.34
     Л
    0.34
     uns
    0.32
     memang
    0.32
     barn
    0.32
     homeowner
    0.32
    uga
    0.31
     затем
    0.31
     właśnie
    0.31
    POSITIVE LOGITS
    对抗
    0.38
    Exponent
    0.37
    hemat
    0.37
     trúc
    0.35
    涩
    0.35
    Single
    0.34
    Hugh
    0.34
    Kant
    0.34
     pcMove
    0.34
    HEMAT
    0.34
    Activations Density 0.000%

    No Known Activations