© 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. 35088
    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
     간
    0.37
    (!
    0.36
    ie
    0.36
    iski
    0.36
     cca
    0.35
     lasting
    0.35
     summarizes
    0.35
     duur
    0.35
     passport
    0.35
     έτσι
    0.35
    POSITIVE LOGITS
     }"
    0.42
     indeterm
    0.40
    sprecher
    0.39
     करवाते
    0.38
     Vit
    0.38
     खरीदते
    0.38
    aldas
    0.37
    !!”
    0.37
    Defocused
    0.37
    魑
    0.36
    Activations Density 0.000%

    No Known Activations