© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45516
    Prev
    Next
    INDEX
    Explanations

    places, hospitals, town, county

    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
     \
    0.48
    >$
    0.47
    VARI
    0.43
    Dark
    0.43
    ָד
    0.42
    قة
    0.42
    .',
    0.41
     móvil
    0.41
    )،
    0.40
    ্শন
    0.40
    POSITIVE LOGITS
     اضافه
    0.51
    la
    0.50
     Doncaster
    0.49
    s
    0.45
    ls
    0.44
    ויות
    0.44
     rejuvenating
    0.44
    uak
    0.44
    uanya
    0.43
    anfaatkan
    0.43
    Activations Density 0.002%

    No Known Activations