© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34895
    Prev
    Next
    INDEX
    Explanations

    extra virgin olive oil

    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_3_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
     is
    0.75
    h
    0.72
     novella
    0.64
     December
    0.62
    does
    0.61
     berapa
    0.60
     warrants
    0.58
     какое
    0.58
    lly
    0.58
     AVENUE
    0.57
    POSITIVE LOGITS
    тор
    0.78
    يش
    0.77
     može
    0.73
    ية
    0.73
    ون
    0.73
    jší
    0.72
    _
    0.71
    ру
    0.71
    وني
    0.71
    يا
    0.71
    Activations Density 0.001%

    No Known Activations