© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44505
    Prev
    Next
    INDEX
    Explanations

    conditional outcomes

    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
     inoculated
    0.44
     ਲ
    0.41
     druž
    0.40
    istor
    0.40
     multiplets
    0.39
     inzwischen
    0.39
    ylvania
    0.39
     piernas
    0.39
    relationship
    0.38
     plumb
    0.38
    POSITIVE LOGITS
    伏
    0.44
    坚持
    0.44
     makes
    0.39
    বস্ত
    0.38
     Basis
    0.38
     asigur
    0.38
    莫
    0.38
    软件
    0.37
     skimage
    0.37
    装
    0.37
    Activations Density 0.000%

    No Known Activations