© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124868
    Prev
    Next
    INDEX
    Explanations

    print statement outputting menu options

    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_37_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
    澀
    0.43
     fiction
    0.42
    urten
    0.38
    μαν
    0.36
     msg
    0.34
    #$%
    0.34
    ][:-
    0.34
    꿀
    0.34
     Andersen
    0.33
     Caramel
    0.33
    POSITIVE LOGITS
    Secondly
    0.40
     ani
    0.40
    distanceArray
    0.38
    नांक
    0.37
     desempen
    0.37
     Episodes
    0.36
    秥
    0.36
    வம்
    0.36
    Exercises
    0.36
     motionProxy
    0.36
    Activations Density 0.002%

    No Known Activations