© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159894
    Prev
    Next
    INDEX
    Explanations

    masochist

    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_2_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
    ني
    1.30
    ور
    1.23
    ا
    1.18
    اب
    1.16
    c
    1.16
    ri
    1.13
    ট
    1.09
    ২
    1.09
    ня
    1.08
    اع
    1.06
    POSITIVE LOGITS
     اکرم
    1.19
    ému
    1.16
    haha
    1.07
     नोटबंदी
    1.05
     врач
    1.05
     सौरभ
    1.05
    0
    1.05
    Сма
    1.04
    u
    1.04
     Davos
    1.01
    Activations Density 0.000%

    No Known Activations