© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212351
    Prev
    Next
    INDEX
    Explanations

    cisgender man/woman/women/gay

    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_5_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
     can
    1.30
     \
    1.13
     você
    1.08
    =\
    1.04
     will
    1.02
    you
    0.98
    その
    0.96
     mă
    0.93
     máu
    0.91
     سایټ
    0.91
    POSITIVE LOGITS
    d
    1.25
    ur
    1.18
    ش
    1.17
    ann
    1.14
    of
    1.14
    st
    1.11
    রা
    1.10
    as
    1.09
    ின்
    1.09
    স
    1.09
    Activations Density 0.000%

    No Known Activations