© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112797
    Prev
    Next
    INDEX
    Explanations

    Ocarina of Time

    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_2_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
     a
    1.23
    ิ
    1.20
     рассказа
    1.10
    の手
    1.08
    an
    1.02
    𝐧
    1.01
     поня
    1.00
    you
    0.99
     powied
    0.98
    a
    0.98
    POSITIVE LOGITS
    д
    1.30
    د
    1.27
    ב
    1.19
    ل
    1.13
    al
    1.09
    <h4>
    1.07
    UM
    1.06
    的
    1.06
    एक
    1.03
     and
    0.99
    Activations Density 0.001%

    No Known Activations