© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104033
    Prev
    Next
    INDEX
    Explanations

    спокій, надто, роки

    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_1_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
    ’
    1.40
    '
    1.10
    ,
    1.08
     that
    1.05
    วิธี
    1.04
    ↵↵
    0.98
     מ
    0.97
     for
    0.95
     injured
    0.94
     ד
    0.94
    POSITIVE LOGITS
    ل
    1.31
    م
    1.30
    ين
    1.14
    ាតុ
    1.12
    ंग
    1.07
    lás
    1.05
     are
    1.02
    ens
    1.02
    鐗
    1.02
    ت
    1.01
    Activations Density 0.000%

    No Known Activations