© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87985
    Prev
    Next
    INDEX
    Explanations

    code or data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    …………………………………………
    0.40
     chalc
    0.38
    傢
    0.37
    ��������
    0.36
     scén
    0.36
    AAAAAAAAAAAAAAAA
    0.36
    إذا
    0.36
    頌
    0.36
     múltipl
    0.35
    ÓN
    0.35
    POSITIVE LOGITS
                        
    0.55
                    
    0.54
                      
    0.54
                       
    0.48
    5
    0.47
    '=>
    0.47
                     
    0.45
    --“
    0.44
     Boolean
    0.43
                   
    0.43
    Activations Density 0.001%

    No Known Activations