© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96778
    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_14_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
    暘
    0.13
    ланды
    0.11
    Ссылки
    0.11
     Pipelines
    0.11
    ດ້ວຍ
    0.11
    ᖁ
    0.11
    ilé
    0.11
     fistule
    0.11
    郄
    0.11
     фут
    0.10
    POSITIVE LOGITS
     announcing
    0.11
    なので
    0.11
     accused
    0.11
    <unused2141>
    0.11
     belum
    0.10
    edly
    0.10
     melihat
    0.10
     Pavlov
    0.10
    颅
    0.10
     acabado
    0.10
    Activations Density 0.005%

    No Known Activations