© 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. 257670
    Prev
    Next
    INDEX
    Explanations

    dropout or resignation

    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
     prehistoric
    0.52
     несмотря
    0.44
    埝
    0.41
    primer
    0.40
    cimentos
    0.39
     modernist
    0.39
    ᱘
    0.38
     pastor
    0.38
     gson
    0.38
    迪士尼
    0.38
    POSITIVE LOGITS
    With
    0.45
     Studies
    0.43
     With
    0.43
    ブン
    0.41
    Modules
    0.40
    ✺
    0.40
     위
    0.39
     API
    0.39
     configuring
    0.39
     câ
    0.38
    Activations Density 0.001%

    No Known Activations