© 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. 161778
    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
     ष
    0.41
     ключ
    0.38
     टेंशन
    0.37
    Keys
    0.37
     ín
    0.37
     समान
    0.36
     cond
    0.35
     Keys
    0.35
     ок
    0.35
     ok
    0.34
    POSITIVE LOGITS
     സ്വാതന്ത്ര
    0.38
     biography
    0.37
    ި
    0.37
    prisoners
    0.36
    sparsebundle
    0.35
     gratuits
    0.35
    athletes
    0.34
    pValue
    0.34
     удиви
    0.33
    גי
    0.33
    Activations Density 0.000%

    No Known Activations