© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132797
    Prev
    Next
    INDEX
    Explanations

    is monkey

    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_1_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
    -
    1.27
    :
    1.24
    ות
    1.13
    েও
    1.10
    <0x80>
    1.09
    них
    1.07
    an
    1.00
    '
    1.00
     дан
    0.98
     awful
    0.98
    POSITIVE LOGITS
    も
    1.45
    。
    1.44
    ও
    1.37
    在
    1.37
    ۔
    1.33
    ）
    1.29
    ។
    1.29
    Я
    1.23
    ።
    1.23
    。)
    1.18
    Activations Density 0.001%

    No Known Activations