© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59129
    Prev
    Next
    INDEX
    Explanations

    names ending in -an, -ian, -osi, -sen

    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
    >
    1.20
    し
    1.14
    ۳
    1.11
    ۵
    1.02
     infidelity
    1.01
    (
    0.98
     layoffs
    0.97
    މ
    0.96
    ]
    0.96
    :
    0.95
    POSITIVE LOGITS
    on
    1.38
    l
    1.16
    ن
    1.04
    an
    1.01
    p
    1.00
    ン
    0.93
    c
    0.93
    ne
    0.88
    ah
    0.88
    lite
    0.87
    Activations Density 0.001%

    No Known Activations