© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198242
    Prev
    Next
    INDEX
    Explanations

    want to build/play

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     لائ
    0.45
    ితే
    0.40
     helping
    0.40
     orçamento
    0.39
    끽
    0.39
     mó
    0.38
    Prop
    0.37
    helping
    0.37
    chir
    0.36
     Kyung
    0.36
    POSITIVE LOGITS
     accepter
    0.45
     akzept
    0.42
     monoxide
    0.42
     ass
    0.41
     accepts
    0.41
     Acceptance
    0.40
     accep
    0.40
     ರಚ
    0.39
     admits
    0.38
    
    0.38
    Activations Density 0.005%

    No Known Activations