© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12543
    Prev
    Next
    INDEX
    Explanations

    what went wrong or differently

    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_13_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
    adder
    0.45
    적
    0.44
    매
    0.43
    아
    0.43
    Без
    0.43
    ide
    0.41
    ат
    0.41
    asset
    0.41
    에
    0.40
    모
    0.40
    POSITIVE LOGITS
     practiced
    0.47
     /**
    0.42
     \#
    0.41
     خير
    0.40
     まま
    0.39
                      
    0.38
     \*
    0.38
     socialize
    0.38
    乡
    0.38
     wholes
    0.38
    Activations Density 0.009%

    No Known Activations