© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81613
    Prev
    Next
    INDEX
    Explanations

    Southwestern regions and styles

    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_0_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
     as
    1.47
     by
    1.16
     οποίο
    1.13
    ﺩ
    1.13
    ס
    1.11
    ק
    1.09
    ލ
    1.06
     UBND
    1.05
     agua
    1.05
     andDevice
    1.04
    POSITIVE LOGITS
    a
    2.34
    u
    2.17
     can
    1.87
    it
    1.84
    o
    1.83
    া
    1.66
    an
    1.63
    .
    1.62
    :
    1.59
    ir
    1.59
    Activations Density 0.001%

    No Known Activations