© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180108
    Prev
    Next
    INDEX
    Explanations

    reports and research

    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_24_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
     $=$
    0.16
    啠
    0.15
     TECHNOLOGY
    0.14
     বিএন
    0.14
    坞
    0.14
    POD
    0.13
     CONTAINER
    0.13
    ᕋ
    0.13
     удоб
    0.13
     Lesson
    0.13
    POSITIVE LOGITS
    และ
    0.17
     आणि
    0.17
     και
    0.16
     और
    0.16
     Kil
    0.15
    vf
    0.15
     và
    0.14
     and
    0.14
     এবং
    0.14
     మరియు
    0.14
    Activations Density 0.010%

    No Known Activations