© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16638
    Prev
    Next
    INDEX
    Explanations

    chapter introduction page count

    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
    Three
    0.50
     трех
    0.48
    THREE
    0.48
    three
    0.46
    三
    0.45
     Three
    0.45
     üç
    0.45
     trois
    0.44
     three
    0.44
    的三
    0.43
    POSITIVE LOGITS
    λικό
    0.38
     soaked
    0.37
     அமிலம்
    0.36
     प्र
    0.36
    לי
    0.35
    женер
    0.35
    郎
    0.35
     blowout
    0.35
    หาร
    0.35
    alten
    0.34
    Activations Density 0.005%

    No Known Activations