© 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. 108251
    Prev
    Next
    INDEX
    Explanations

    Iraq

    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
    '}
    1.13
     Drž
    0.96
    ↵↵
    0.92
     Puede
    0.90
    );}
    0.88
     hará
    0.88
     форма
    0.88
    <unused60>
    0.84
    مي
    0.84
    '};
    0.84
    POSITIVE LOGITS
    ート
    1.05
    ων
    1.05
     flywheel
    1.02
    ючи
    1.00
     brisket
    0.97
    ین
    0.95
    ه‌ی
    0.93
    ene
    0.91
    age
    0.90
     cytokines
    0.90
    Activations Density 0.000%

    No Known Activations