© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17847
    Prev
    Next
    INDEX
    Explanations

    )

    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
     エネルギー
    0.14
    WHAT
    0.14
    斯的
    0.13
    եղ
    0.13
    <unused2200>
    0.13
    HEL
    0.13
    HIP
    0.13
    ಎಸ್
    0.13
    落在
    0.13
    CHA
    0.13
    POSITIVE LOGITS
     deportivos
    0.13
     success
    0.13
     hasta
    0.12
    :
    0.12
     Andre
    0.12
    şi
    0.12
     successo
    0.12
    ienza
    0.11
     successor
    0.11
     Hasta
    0.11
    Activations Density 0.287%

    No Known Activations