© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212552
    Prev
    Next
    INDEX
    Explanations

    diverse causal or consequential phrases

    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_5_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
     =
    1.38
     {
    1.19
     (
    1.14
    1.14
    _
    1.13
     K
    1.09
      
    1.06
     eller
    1.02
     A
    1.01
     +
    1.00
    POSITIVE LOGITS
    ہ
    1.54
    ک
    1.20
    ди
    1.17
    более
    1.16
    ϲ
    1.16
     определён
    1.13
    یر
    1.12
    ယ့်
    1.11
    élève
    1.09
    𝒗
    1.09
    Activations Density 0.000%

    No Known Activations