© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23416
    Prev
    Next
    INDEX
    Explanations

    Spanish past participles

    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_56_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
    ני
    0.51
    רה
    0.41
     effortless
    0.38
    διο
    0.37
    nian
    0.37
    嘉
    0.37
     indis
    0.36
    🌓
    0.36
    日付
    0.36
     resting
    0.35
    POSITIVE LOGITS
    izado
    0.77
    ionado
    0.71
    ificado
    0.69
    inado
    0.68
    ivado
    0.66
    ADO
    0.66
    ado
    0.64
    iado
    0.62
    iciado
    0.62
    orado
    0.61
    Activations Density 0.033%

    No Known Activations