© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53933
    Prev
    Next
    INDEX
    Explanations

    project planning items

    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
    ♯
    0.41
     Encyclopædia
    0.40
    ெட்
    0.40
     \...
    0.38
     वरना
    0.36
     ਚ
    0.36
    ෲ
    0.36
    পালের
    0.36
    igt
    0.35
     pathogenesis
    0.35
    POSITIVE LOGITS
    
    0.42
     scoping
    0.40
    
    0.37
    onymous
    0.37
     (“
    0.35
    uksia
    0.34
    兩
    0.34
     نفر
    0.34
    (“
    0.34
    
    0.34
    Activations Density 0.017%

    No Known Activations