© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90681
    Prev
    Next
    INDEX
    Explanations

    demilitarization, demethylation, demultiplex

    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_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
    Demand
    1.08
     demand
    1.01
     Demand
    1.01
    demand
    0.96
    and
    0.84
     demanded
    0.83
    R
    0.83
    MS
    0.81
    ME
    0.81
    X
    0.80
    POSITIVE LOGITS
    "。
    0.75
    .。
    0.72
    ف
    0.70
    на
    0.66
    ็ว
    0.65
    ющих
    0.64
    ните
    0.63
    。
    0.63
    니다
    0.61
     сервис
    0.61
    Activations Density 0.008%

    No Known Activations