© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206094
    Prev
    Next
    INDEX
    Explanations

    misspellings and replacements

    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_37_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
     Thay
    0.40
     settle
    0.38
     thay
    0.37
     Territories
    0.36
     )
    0.35
     ಉತ್ತ
    0.35
    Thay
    0.35
    䉽
    0.34
    চীন
    0.34
    ဲ့
    0.34
    POSITIVE LOGITS
     observational
    0.41
    locality
    0.40
    ٰ
    0.36
     Übersetzung
    0.36
     মতে
    0.35
    virt
    0.35
     lifestyle
    0.35
     ইসলামিক
    0.34
     மோ
    0.34
    factorplot
    0.34
    Activations Density 0.010%

    No Known Activations