© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234848
    Prev
    Next
    INDEX
    Explanations

    there vs their vs they're

    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_32_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
     ボタン
    0.39
    Fab
    0.38
    stone
    0.35
    umbuhan
    0.35
    കല
    0.34
    FormatException
    0.34
    Ok
    0.33
    띠
    0.33
    Kir
    0.33
    veget
    0.33
    POSITIVE LOGITS
     Tenemos
    0.38
     প্রতীক
    0.38
     लूट
    0.38
     Phon
    0.38
     सोन
    0.38
     Lobkovic
    0.36
     spelling
    0.36
     vowel
    0.36
     Besoin
    0.36
     Hormone
    0.35
    Activations Density 0.005%

    No Known Activations