© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202136
    Prev
    Next
    INDEX
    Explanations

    Homo sapiens and other Homo species

    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_6_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
     Κ
    1.09
     КО
    1.09
     beş
    1.07
    О
    1.07
     DOA
    1.01
     PVA
    1.00
     Α
    0.98
     GoPro
    0.98
     ВС
    0.98
     Ζ
    0.96
    POSITIVE LOGITS
    \
    1.04
    ad
    1.03
    ide
    1.00
    ä
    0.97
    í
    0.93
    u
    0.92
    led
    0.89
    <\
    0.88
    {
    0.87
    icks
    0.87
    Activations Density 0.000%

    No Known Activations