© 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. 58743
    Prev
    Next
    INDEX
    Explanations

    limiting

    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
    ка
    1.02
    <0xA0>
    0.97
    ра
    0.97
    ду
    0.93
    <0xBE>
    0.84
    的时
    0.84
    <0x97>
    0.84
    <0xB7>
    0.80
     في
    0.80
     পেয়ে
    0.80
    POSITIVE LOGITS
     for
    1.66
     and
    1.54
    and
    1.51
    ل
    1.40
    is
    1.39
    i
    1.32
    u
    1.30
    es
    1.29
    n
    1.27
    د
    1.25
    Activations Density 0.002%

    No Known Activations