© 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. 162748
    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
     flap
    0.37
     harness
    0.36
    linger
    0.36
     meson
    0.35
     flaps
    0.35
    amientos
    0.35
    )>\
    0.34
     numerador
    0.34
    sling
    0.34
    剷
    0.34
    POSITIVE LOGITS
    യ്
    0.39
    珩
    0.38
    梔
    0.36
    未
    0.35
     мі
    0.34
     Squirrel
    0.34
     Dot
    0.34
     immortality
    0.34
     Carter
    0.33
     банка
    0.32
    Activations Density 0.000%

    No Known Activations