© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220328
    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_31_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
    mersible
    0.50
     impresora
    0.38
    દર
    0.38
     seabed
    0.38
    satellite
    0.37
    镜头
    0.37
     Webcam
    0.37
    夥
    0.37
    Mbps
    0.36
    camera
    0.36
    POSITIVE LOGITS
     obtains
    0.38
    फेक्शन
    0.37
    inois
    0.36
     unfortunately
    0.35
     ARTHUR
    0.35
     धनु
    0.35
     mamm
    0.34
     pourtant
    0.34
    ρή
    0.34
    我认为
    0.34
    Activations Density 0.000%

    No Known Activations