© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178538
    Prev
    Next
    INDEX
    Explanations

    important, crucial, needs

    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_29_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
    ባድ
    0.34
    要求
    0.32
     MAM
    0.30
    要求的
    0.29
    必ず
    0.27
     তত্ত্বাব
    0.27
     꼭
    0.27
    
    0.27
    Always
    0.27
    必须要
    0.27
    POSITIVE LOGITS
    لاص
    0.31
    cccccc
    0.30
     remand
    0.29
    ঠা
    0.29
     compactness
    0.29
     Geißler
    0.29
     traction
    0.29
     bothered
    0.29
    inguistic
    0.29
     foes
    0.28
    Activations Density 0.012%

    No Known Activations