© 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. 80134
    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
    𝙙
    0.41
     ث
    0.39
     MgII
    0.39
     స్వ
    0.38
     забезпе
    0.37
     прекра
    0.37
     Lapse
    0.37
    TRAVEL
    0.37
    णाला
    0.36
    𝗇
    0.36
    POSITIVE LOGITS
    Zam
    0.37
     nourrice
    0.36
    íbrio
    0.36
     annotated
    0.34
    ందా
    0.34
     चाहर
    0.34
    PubMed
    0.34
    收
    0.34
    之上
    0.33
     libras
    0.33
    Activations Density 0.000%

    No Known Activations