© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109191
    Prev
    Next
    INDEX
    Explanations

    Asiana Airlines

    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
    dı
    1.18
    tı
    1.10
    dh
    1.01
    crs
    1.00
    ת
    0.99
    crt
    0.99
    cF
    0.98
     đợi
    0.96
    druck
    0.96
    tp
    0.95
    POSITIVE LOGITS
    ות
    1.16
    나
    1.12
    1
    1.06
    ),
    1.02
    ీయ
    1.02
    ak
    0.99
    on
    0.95
    iodate
    0.95
    ).
    0.94
    Б
    0.93
    Activations Density 0.000%

    No Known Activations