© 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. 121699
    Prev
    Next
    INDEX
    Explanations

    elderly individuals

    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
    0.80
     établ
    0.72
    ات
    0.71
     fourn
    0.71
    .
    0.63
     obstruct
    0.62
    ”
    0.62
    ర్
    0.60
    }}$,
    0.60
    ט
    0.60
    POSITIVE LOGITS
     are
    0.82
    ка
    0.72
    お金
    0.70
    ご
    0.69
     आंकड़ों
    0.65
    াস
    0.61
    )」
    0.57
    かかる
    0.57
     favored
    0.57
     შორის
    0.57
    Activations Density 0.000%

    No Known Activations