© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34084
    Prev
    Next
    INDEX
    Explanations

    knock-knock jokes

    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_31_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
    矵
    0.40
     문제는
    0.39
    duğu
    0.38
    aktur
    0.38
     Dubey
    0.37
    잎
    0.37
     سخ
    0.36
     $<\
    0.36
    СП
    0.36
    是为了
    0.36
    POSITIVE LOGITS
     who
    0.61
    who
    0.55
     whom
    0.48
     Who
    0.48
    what
    0.47
    Кто
    0.47
    Who
    0.46
     what
    0.46
     quien
    0.45
     quién
    0.44
    Activations Density 0.001%

    No Known Activations