© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45412
    Prev
    Next
    INDEX
    Explanations

    time periods and conditions

    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
    ก
    1.16
    ת
    0.92
    at
    0.85
    บ
    0.82
    y
    0.80
     to
    0.79
    ן
    0.73
    ی
    0.73
    ή
    0.71
     amortization
    0.70
    POSITIVE LOGITS
    3
    0.74
    0
    0.68
    ;
    0.67
    ージャー
    0.64
     말미암아
    0.63
    Ownership
    0.61
        
    0.59
    <code>
    0.58
    <h3>
    0.57
                                
    0.57
    Activations Density 0.010%

    No Known Activations