© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14319
    Prev
    Next
    INDEX
    Explanations

    css frameworks and libraries

    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_34_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
     scaler
    0.40
     imageHeight
    0.39
    iyati
    0.37
     ലാ
    0.37
    Bus
    0.37
    Businesses
    0.37
     `<=`
    0.36
    Tolerance
    0.36
     quoting
    0.35
    პერ
    0.35
    POSITIVE LOGITS
     ምር
    0.43
    ୈ
    0.39
     عج
    0.38
     assi
    0.38
     Whirl
    0.36
    css
    0.36
    톤
    0.36
     produ
    0.36
     পছন্দ
    0.36
     Relativity
    0.35
    Activations Density 0.001%

    No Known Activations