© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14478
    Prev
    Next
    INDEX
    Explanations

    delivery

    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_15_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
    ↵
    0.62
     being
    0.59
     fiind
    0.54
     var
    0.49
     which
    0.49
    st
    0.48
     testing
    0.48
    )、
    0.48
    );
    0.47
     Und
    0.47
    POSITIVE LOGITS
     Стаўкі
    0.54
    vvvert
    0.51
    Ἑ
    0.51
    िरपेक्ष
    0.50
    брать
    0.49
     aparentemente
    0.49
     moteurs
    0.49
     पदों
    0.49
    ہائی
    0.49
    мены
    0.48
    Activations Density 0.009%

    No Known Activations