© 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. 80841
    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
     Mous
    0.44
     mous
    0.39
     Hubbard
    0.36
     पश्चात
    0.36
     intervalles
    0.36
     intervalos
    0.35
    डेट
    0.35
    擢
    0.35
     interval
    0.35
    ško
    0.35
    POSITIVE LOGITS
     agitation
    0.43
    ক্কা
    0.38
     Cyborg
    0.35
     inviol
    0.34
    侕
    0.34
     داش
    0.34
     casado
    0.34
     grits
    0.33
     KSI
    0.33
     foodie
    0.33
    Activations Density 0.000%

    No Known Activations