© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44461
    Prev
    Next
    INDEX
    Explanations

    regular and irregular verbs

    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_13_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
    גר
    0.48
    лась
    0.44
    gge
    0.43
    gga
    0.40
    Př
    0.40
    ﺧ
    0.40
    ppb
    0.39
    ﮐ
    0.39
    މ
    0.39
     یک
    0.38
    POSITIVE LOGITS
     omdat
    0.54
     ogrom
    0.52
     treacherous
    0.50
     water
    0.49
     enormous
    0.49
     Oliv
    0.48
     weapons
    0.47
     ammunition
    0.47
     shoot
    0.47
     weapon
    0.47
    Activations Density 0.051%

    No Known Activations