© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51754
    Prev
    Next
    INDEX
    Explanations

    experimental task

    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_30_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
     Analysis
    0.41
     bk
    0.38
     Correlation
    0.37
     Richards
    0.37
     trimmer
    0.37
     Sophia
    0.36
    ":{"
    0.35
    驄
    0.34
     ANALYSIS
    0.34
    ోతి
    0.34
    POSITIVE LOGITS
     obesity
    0.44
    ፈጥ
    0.40
     obese
    0.38
     naturl
    0.38
     obligatoire
    0.38
     desn
    0.38
     artificially
    0.38
    arante
    0.37
     devastating
    0.37
     mempel
    0.37
    Activations Density 0.026%

    No Known Activations