© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66775
    Prev
    Next
    INDEX
    Explanations

    general idea is sufficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    Shark
    0.38
    못
    0.37
    你能
    0.37
    你们
    0.37
     Ihr
    0.36
    以来
    0.36
    妳
    0.36
    시오
    0.36
    你知道
    0.36
    您的
    0.35
    POSITIVE LOGITS
     suffice
    1.27
     suffices
    1.20
     sufficient
    1.13
     suffit
    1.02
     Sufficient
    1.01
     suffisante
    1.01
    sufficient
    0.97
     Suff
    0.96
     sufficiency
    0.96
     suficiente
    0.93
    Activations Density 0.005%

    No Known Activations