© 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. 262014
    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
    浏
    0.49
     incorpora
    0.48
    검
    0.48
     litros
    0.46
    부
    0.46
    сцю
    0.45
    ψε
    0.45
     рэгістрацыі
    0.45
    꼬
    0.44
    с
    0.44
    POSITIVE LOGITS
    DIST
    0.50
     STATIC
    0.46
    alogy
    0.46
    恩
    0.44
     jihad
    0.44
     Jihad
    0.44
    AIN
    0.43
     Static
    0.42
     encephal
    0.41
    OGRAPHIC
    0.41
    Activations Density 0.000%

    No Known Activations