© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210554
    Prev
    Next
    INDEX
    Explanations

    eat or consume

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     взя
    0.89
    Taking
    0.89
    取
    0.87
     taken
    0.87
    Taken
    0.85
     taking
    0.82
     Taking
    0.82
     Taken
    0.81
     취
    0.81
    taken
    0.80
    POSITIVE LOGITS
     consume
    1.32
     consuming
    1.30
     consumed
    1.19
     consumo
    1.19
     consumes
    1.19
     consumption
    1.16
     Consume
    1.16
     eat
    1.13
     eating
    1.13
     Consumption
    1.13
    Activations Density 0.014%

    No Known Activations