© 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. 216531
    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
     Shared
    0.38
    能力的
    0.38
    迤
    0.38
     Flick
    0.37
     alemán
    0.36
     pequenos
    0.36
    用来
    0.36
    Ah
    0.35
    Shared
    0.35
     Provider
    0.35
    POSITIVE LOGITS
    iram
    0.42
    糊
    0.39
     belated
    0.36
     lamb
    0.36
    }$}
    0.35
     snail
    0.35
    adillo
    0.35
     xyz
    0.35
    endig
    0.35
    अरविंद
    0.34
    Activations Density 0.000%

    No Known Activations