© 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. 162548
    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
     sot
    0.43
    decompose
    0.42
    kość
    0.39
     Sot
    0.38
     antidote
    0.38
     literacy
    0.37
    偿
    0.37
    மோ
    0.35
     Dism
    0.35
    मेट
    0.35
    POSITIVE LOGITS
     incorrectly
    0.39
     ISLAND
    0.37
     потреби
    0.36
     себе
    0.35
     Sheridan
    0.35
    вича
    0.34
     pws
    0.34
    ▇
    0.33
    𒂗
    0.33
    êmes
    0.33
    Activations Density 0.000%

    No Known Activations