© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23673
    Prev
    Next
    INDEX
    Explanations

    sixth

    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_56_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
     Three
    0.75
    Three
    0.75
    三
    0.73
     three
    0.70
    three
    0.69
     drei
    0.68
     THREE
    0.65
     trois
    0.64
     ثلاث
    0.64
     थ्री
    0.64
    POSITIVE LOGITS
     sixth
    0.63
                
    0.59
                 
    0.54
     sexto
    0.54
    Sixth
    0.53
     Sixth
    0.52
                    
    0.51
     六
    0.49
     seventh
    0.48
                   
    0.48
    Activations Density 0.018%

    No Known Activations