© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50989
    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_10_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
    t
    0.55
     Identify
    0.53
     IT
    0.49
    ],
    0.47
     Factor
    0.46
     Seamless
    0.46
     identify
    0.46
     ANY
    0.45
     Titanium
    0.44
     TT
    0.43
    POSITIVE LOGITS
     academies
    0.50
    اللي
    0.46
     gunmen
    0.46
     დარ
    0.46
    Lore
    0.45
    ابر
    0.45
    Bihar
    0.44
    ᱖
    0.44
    Promises
    0.44
     اولى
    0.44
    Activations Density 0.000%

    No Known Activations