© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43107
    Prev
    Next
    INDEX
    Explanations

    MARC and DMARDs

    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
    지에
    0.86
    用
    0.76
    지
    0.76
    지와
    0.73
    िंग
    0.70
    ीकरण
    0.68
    பின்
    0.67
    ِلِّ
    0.67
    乆
    0.65
    洴
    0.65
    POSITIVE LOGITS
     on
    0.86
    E
    0.73
    il
    0.71
    K
    0.71
    X
    0.71
    Angle
    0.69
     wyb
    0.66
    O
    0.66
     יש
    0.66
    し
    0.65
    Activations Density 0.000%

    No Known Activations