© 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. 23723
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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
    ės
    0.75
     tai
    0.75
    čių
    0.74
    ų
    0.70
    ė
    0.68
     tiet
    0.67
    ėj
    0.67
    ėl
    0.66
    čio
    0.66
    žių
    0.66
    POSITIVE LOGITS
     asegurar
    0.38
     покра
    0.37
    ('['
    0.36
     शब्दों
    0.35
     catech
    0.35
     assurances
    0.34
     galore
    0.34
    figures
    0.34
     genes
    0.34
     середи
    0.34
    Activations Density 0.001%

    No Known Activations