© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103760
    Prev
    Next
    INDEX
    Explanations

    光 (light) followed by various words

    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_1_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
    ت
    1.53
    м
    1.12
    ில்
    1.04
    r
    1.04
    ل
    0.98
    <0x80>
    0.95
    ம்
    0.95
    т
    0.94
    t
    0.92
    م
    0.92
    POSITIVE LOGITS
     of
    1.62
    of
    1.38
     as
    1.22
    ма
    1.20
     is
    1.14
    의
    1.07
    Name
    1.03
     variado
    0.99
    ні
    0.98
        
    0.98
    Activations Density 0.000%

    No Known Activations