© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40837
    Prev
    Next
    INDEX
    Explanations

    sexual orientation

    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
     ketones
    0.66
    R
    0.66
     aliphatic
    0.66
     materially
    0.63
     edición
    0.63
    ꯣ
    0.62
     sparsim
    0.62
     цена
    0.61
    stoi
    0.61
     стаўкі
    0.60
    POSITIVE LOGITS
    ור
    0.96
    ل
    0.95
    ת
    0.94
    ون
    0.93
    ల
    0.84
    .
    0.83
    خدام
    0.75
    ல்
    0.74
    ून
    0.73
    רים
    0.73
    Activations Density 0.005%

    No Known Activations