© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163969
    Prev
    Next
    INDEX
    Explanations

    ranking methods

    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_13_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
     >
    0.29
     विश्लेषण
    0.28
     ٹرسٹ
    0.28
    事故
    0.28
    噛
    0.28
     ferry
    0.27
    薔
    0.27
    ɻ
    0.26
    锅
    0.26
    அ
    0.25
    POSITIVE LOGITS
    )).
    0.29
    )\
    0.26
    води
    0.25
    ),
    0.25
    গানি
    0.25
    ));
    0.25
     fortemente
    0.24
    )["
    0.24
    ânea
    0.24
    ჯ
    0.24
    Activations Density 0.002%

    No Known Activations