© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125915
    Prev
    Next
    INDEX
    Explanations

    rules, types, or specific components

    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
    يل
    0.84
    و
    0.77
    的他
    0.70
    ס
    0.70
    ți
    0.68
    ം
    0.67
    姆
    0.66
    ור
    0.65
    ৬
    0.64
    ం
    0.63
    POSITIVE LOGITS
    t
    0.84
     incisions
    0.72
    ت
    0.72
    т
    0.69
     enthalpies
    0.67
    一
    0.65
     capacitances
    0.64
     seizures
    0.63
     границ
    0.63
     QSOs
    0.63
    Activations Density 0.004%

    No Known Activations