© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43776
    Prev
    Next
    INDEX
    Explanations

    boy or girl groups

    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_3_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
    t
    1.01
    i
    0.80
    in
    0.71
    the
    0.64
    ت
    0.63
    정에
    0.62
    e
    0.61
    d
    0.61
     stava
    0.58
    r
    0.58
    POSITIVE LOGITS
     of
    0.87
     are
    0.84
     be
    0.82
    0.79
    یت
    0.75
    ă
    0.73
    ல்
    0.71
     is
    0.71
    р
    0.66
    ರನ್ನು
    0.65
    Activations Density 0.000%

    No Known Activations