© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110060
    Prev
    Next
    INDEX
    Explanations

    posible, weight, elet, adres, instal

    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_2_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
    on
    1.23
    is
    1.05
    ת
    1.05
    Z
    1.05
    ня
    1.01
    ן
    0.99
    has
    0.98
    nity
    0.96
    um
    0.96
    و
    0.96
    POSITIVE LOGITS
    ある
    1.48
    د
    1.16
     can
    1.15
     are
    1.14
    お金
    1.14
    ре
    1.13
    おお
    1.13
     estampado
    1.13
    ра
    1.11
     añad
    1.09
    Activations Density 0.000%

    No Known Activations