© 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. 125205
    Prev
    Next
    INDEX
    Explanations

    Guinness World Records

    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
    ing
    0.78
    ת
    0.70
    ية
    0.68
    ير
    0.63
    وا
    0.63
    то
    0.62
    inizi
    0.62
     fester
    0.62
     was
    0.61
    ك
    0.61
    POSITIVE LOGITS
    ವ್
    0.70
    meshes
    0.68
    dalam
    0.64
    served
    0.63
    novation
    0.61
    amentos
    0.60
    یت
    0.58
    baik
    0.58
    NAMEN
    0.58
    direct
    0.57
    Activations Density 0.000%

    No Known Activations