© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8607
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    toxicity
    1.56
    𝗯
    1.54
     WAN
    1.52
    ा
    1.50
    Natal
    1.48
    going
    1.46
    ब्दिक
    1.45
     ा
    1.43
    
    1.43
    
    1.43
    POSITIVE LOGITS
    お得
    1.61
     defaultdict
    1.57
    σ
    1.50
     plano
    1.48
    ون
    1.41
    ين
    1.41
    л
    1.37
     možnost
    1.36
    ismer
    1.34
     drawstring
    1.34
    Activations Density 0.052%

    No Known Activations