© 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. 42931
    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
     “.
    0.48
    द्धाल
    0.45
    ེ
    0.45
     Direktor
    0.45
     Accumulated
    0.45
     subdivisions
    0.44
    체를
    0.44
     Charl
    0.43
     ficción
    0.43
     Rami
    0.43
    POSITIVE LOGITS
    apped
    0.45
    ayak
    0.45
    aked
    0.44
    urm
    0.44
    ј
    0.42
    rive
    0.42
     deemed
    0.42
     لما
    0.41
    ilaire
    0.41
     deems
    0.41
    Activations Density 0.000%

    No Known Activations