© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196516
    Prev
    Next
    INDEX
    Explanations

    sano / rasp / sarro

    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_4_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
     of
    1.17
    ลูกค้า
    0.92
     on
    0.92
    સ
    0.86
    nya
    0.83
    ลูก
    0.81
    ای
    0.80
     llamadas
    0.80
    กัน
    0.79
    ของ
    0.79
    POSITIVE LOGITS
    at
    0.94
    ро
    0.94
    oc
    0.86
    ো
    0.82
    ၄
    0.82
    ур
    0.82
    ير
    0.81
    ру
    0.80
    ö
    0.80
    ков
    0.78
    Activations Density 0.006%

    No Known Activations