© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5920
    Prev
    Next
    INDEX
    Explanations

    theory of relativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ار
    3.40
    m
    3.17
    ため
    3.13
    એ
    2.96
    mz
    2.91
    ículas
    2.76
    zahlen
    2.71
    estone
    2.69
     obt
    2.63
    लिये
    2.61
    POSITIVE LOGITS
     relativity
    2.94
    
    2.69
     sayang
    2.65
                        
    2.61
    姆
    2.61
    <0x0D>
    2.56
    atelle
    2.52
    eradish
    2.47
     посад
    2.47
    徉
    2.39
    Activations Density 0.040%

    No Known Activations