© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176212
    Prev
    Next
    INDEX
    Explanations

    increased risk

    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_24_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
     круг
    0.26
     тро
    0.26
     (/
    0.25
     Между
    0.25
     Тро
    0.24
     Lakeland
    0.23
     алфа
    0.22
     เร
    0.22
     квадрат
    0.22
    叹
    0.22
    POSITIVE LOGITS
     hool
    0.26
     huo
    0.26
    hentication
    0.25
     leverage
    0.25
     certo
    0.25
     ciertas
    0.24
    posizione
    0.24
    pyraz
    0.24
    GORITHM
    0.24
    ées
    0.24
    Activations Density 0.006%

    No Known Activations