© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210722
    Prev
    Next
    INDEX
    Explanations

    avoiding certain terms or methods

    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_20_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
     Veterans
    0.39
     금액
    0.39
    usalem
    0.36
     olma
    0.35
    hok
    0.35
    </h5>
    0.35
    uma
    0.34
     अर्
    0.34
     기록
    0.34
     kadang
    0.34
    POSITIVE LOGITS
    ∆
    0.38
    Slip
    0.38
    Scar
    0.36
    Flat
    0.36
    πλ
    0.36
     decou
    0.36
    Vector
    0.35
    Все
    0.35
    Minimize
    0.35
     nouveau
    0.34
    Activations Density 0.052%

    No Known Activations