© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146070
    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_59_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
    Identification
    0.47
     Identification
    0.42
    identification
    0.40
     Hearing
    0.39
    /(
    0.39
    Strategy
    0.39
    hearing
    0.38
    ffiti
    0.38
     Parsing
    0.38
    )/(
    0.37
    POSITIVE LOGITS
    ige
    0.72
     brune
    0.56
     groene
    0.55
    ielle
    0.52
    iske
    0.52
    rlige
    0.50
    elijke
    0.49
    ieke
    0.49
     spezielle
    0.48
    IGE
    0.48
    Activations Density 0.000%

    No Known Activations