© 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. 42060
    Prev
    Next
    INDEX
    Explanations

    running executable files

    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
     बता
    0.45
    bean
    0.44
     Kann
    0.42
    bagi
    0.40
     brews
    0.40
    joe
    0.40
    滷
    0.40
    bear
    0.39
     kisi
    0.39
    कै
    0.39
    POSITIVE LOGITS
    ContentLoaded
    0.44
    UiThread
    0.43
    弹
    0.43
    弹性
    0.43
    putnik
    0.40
    Forever
    0.40
    WhiteBalance
    0.40
    盜
    0.39
     gift
    0.39
    ESSITY
    0.39
    Activations Density 0.004%

    No Known Activations