© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257905
    Prev
    Next
    INDEX
    Explanations

    when using/making/writing/doing/creating

    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_22_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
     فه
    0.44
     devil
    0.43
    ๘
    0.43
     ম
    0.40
    ↵↵↵↵
    0.40
     Música
    0.40
     transitory
    0.39
    ктор
    0.39
    㶱
    0.39
    唓
    0.39
    POSITIVE LOGITS
     antr
    0.47
     oversaw
    0.41
    Ꭸ
    0.41
    flatten
    0.41
     konten
    0.41
     hens
    0.40
    obei
    0.40
     outputs
    0.39
    ্বস্ত
    0.39
     annot
    0.39
    Activations Density 0.001%

    No Known Activations