© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36559
    Prev
    Next
    INDEX
    Explanations

    FEA simulation

    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_3_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
    م
    1.10
    м
    0.83
    ம்
    0.77
    tı
    0.75
    ری
    0.74
    ة
    0.74
    مند
    0.66
    다
    0.65
    نی
    0.64
    t
    0.64
    POSITIVE LOGITS
    '
    0.93
    ’
    0.89
    is
    0.75
    ين
    0.74
    EN
    0.71
    ’”
    0.70
     בדי
    0.68
    𝟐
    0.66
     futhi
    0.66
     izay
    0.64
    Activations Density 0.006%

    No Known Activations