© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146556
    Prev
    Next
    INDEX
    Explanations

    let's

    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_18_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
    :
    0.32
      
    0.32
    ac
    0.32
       
    0.31
    ips
    0.30
    .
    0.30
     which
    0.29
    \.
    0.29
    =
    0.29
     बाय
    0.28
    POSITIVE LOGITS
     edificios
    0.39
    Imagem
    0.37
     fossero
    0.37
    机场
    0.37
     Bhagavato
    0.37
    ْم
    0.36
    甪
    0.36
    ЕН
    0.35
     আর্মির
    0.35
    Я
    0.35
    Activations Density 0.015%

    No Known Activations