© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199847
    Prev
    Next
    INDEX
    Explanations

    names of people or entities

    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_12_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
    وم
    0.54
     медицин
    0.54
     의료
    0.53
    <0x0D>
    0.52
     diambil
    0.49
     viêm
    0.49
     μικ
    0.49
     फ
    0.48
    医療
    0.48
     신경
    0.48
    POSITIVE LOGITS
    phalt
    0.57
     Tal
    0.53
    onics
    0.53
    ungk
    0.52
    yn
    0.51
    eaa
    0.50
    onte
    0.50
    oked
    0.49
     Haber
    0.49
    oner
    0.49
    Activations Density 0.000%

    No Known Activations