© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28483
    Prev
    Next
    INDEX
    Explanations

    foreclosure

    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_40_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
    hensible
    0.42
    acic
    0.40
    ﻱ
    0.37
     NASCAR
    0.36
     Situ
    0.36
     mic
    0.35
     reproduce
    0.35
    粙
    0.35
    中学
    0.35
     liegt
    0.34
    POSITIVE LOGITS
     confirming
    0.39
     Castillo
    0.39
     heb
    0.37
     Совет
    0.37
     বিভ
    0.37
    ovation
    0.36
     рациона
    0.36
     পাশ
    0.36
     আভ
    0.36
     hav
    0.35
    Activations Density 0.003%

    No Known Activations