© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257877
    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_22_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
    ás
    0.51
    akam
    0.46
    Б
    0.46
    ákat
    0.46
    rok
    0.45
     سرب
    0.44
    TE
    0.44
    üyük
    0.44
    ashita
    0.44
    ﺍ
    0.43
    POSITIVE LOGITS
    ありません
    0.59
    плення
    0.51
     Pathology
    0.47
     Ontology
    0.46
     mobilization
    0.46
     mobil
    0.45
     pathology
    0.45
     ventilation
    0.43
     specialization
    0.43
    激光
    0.43
    Activations Density 0.000%

    No Known Activations