© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56838
    Prev
    Next
    INDEX
    Explanations

    efficiently or efficient

    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_11_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
     -
    0.40
    athe
    0.40
     j
    0.39
     di
    0.35
    api
    0.35
    apak
    0.35
     =
    0.35
    )!
    0.35
     ut
    0.35
     Foto
    0.34
    POSITIVE LOGITS
    لاع
    0.36
     زود
    0.36
     striis
    0.32
     blocs
    0.32
    IOD
    0.31
    Recognition
    0.31
    Emple
    0.31
    Hoist
    0.31
     전에
    0.30
     gesturing
    0.30
    Activations Density 0.010%

    No Known Activations