© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194998
    Prev
    Next
    INDEX
    Explanations

    configuration file names

    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_4_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
    ма
    1.01
    م
    1.01
    в
    1.00
    сці
    0.91
    м
    0.90
    ره
    0.86
    t
    0.86
    ને
    0.85
    ဩ
    0.84
    яс
    0.83
    POSITIVE LOGITS
    ;
    1.65
     can
    1.29
    ,
    1.17
     y
    1.16
     as
    1.12
     have
    1.08
     juga
    1.02
    ir
    1.00
     s
    0.99
    .
    0.98
    Activations Density 0.002%

    No Known Activations