© 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. 53480
    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
     பேரும்
    0.34
    chow
    0.34
     සම
    0.33
    amb
    0.32
     sonore
    0.32
    elhos
    0.32
    観
    0.32
     plán
    0.31
     kıl
    0.31
     ambit
    0.31
    POSITIVE LOGITS
    佤
    0.39
     स्कैनर
    0.36
    Bronze
    0.34
    Coul
    0.34
    Kul
    0.34
     Culture
    0.34
    Bes
    0.34
     Bronze
    0.34
     microseconds
    0.33
     প্রশাস
    0.33
    Activations Density 0.000%

    No Known Activations