© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33722
    Prev
    Next
    INDEX
    Explanations

    front and center, verbal

    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
    د
    0.66
    ی
    0.65
    ो
    0.64
    си
    0.64
    র
    0.60
     نگر
    0.60
    ิ
    0.60
    شک
    0.59
     Obat
    0.59
    стройства
    0.59
    POSITIVE LOGITS
    un
    0.75
    IA
    0.69
    ado
    0.61
    是
    0.58
    ame
    0.57
    ంత
    0.56
    ido
    0.55
    ಂಬ
    0.55
    োগ
    0.55
    ian
    0.54
    Activations Density 0.003%

    No Known Activations