© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164539
    Prev
    Next
    INDEX
    Explanations

    navigate it

    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_31_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
     incite
    0.40
     parallel
    0.38
     multiplicity
    0.37
     parallels
    0.37
     similarities
    0.36
    ಏ
    0.35
     concomitant
    0.34
     多い
    0.34
     intimacy
    0.34
     dovet
    0.34
    POSITIVE LOGITS
    ℠
    0.36
    
    0.35
    ]'
    0.33
    arian
    0.32
     wabarakatuh
    0.32
     जॉर्ज
    0.31
    ]."
    0.31
    ]^{\
    0.30
     сал
    0.30
     ጡ
    0.30
    Activations Density 0.013%

    No Known Activations