© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176230
    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_24_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
    𝗸
    0.46
    選手
    0.43
    🥲
    0.42
     nejen
    0.41
    Equipo
    0.41
    -->
    0.41
    窒
    0.41
    fruits
    0.41
     rightfully
    0.40
    ݢ
    0.40
    POSITIVE LOGITS
     ஒரு
    0.43
     ili
    0.40
     Londres
    0.40
     relativity
    0.39
     microwaves
    0.39
    தேச
    0.38
    ités
    0.38
     Bakersfield
    0.38
     odred
    0.38
     suatu
    0.37
    Activations Density 0.000%

    No Known Activations