© 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. 109472
    Prev
    Next
    INDEX
    Explanations

    urls ending in </

    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
     in
    1.34
    ৯
    1.32
    لم
    1.20
    но
    1.16
    ৭
    1.15
    и
    1.14
    도
    1.12
    ز
    1.09
    在
    1.07
    ين
    1.04
    POSITIVE LOGITS
     to
    1.14
    く
    1.05
     and
    1.02
    ;
    1.02
    ],
    1.00
    S
    0.99
    DA
    0.97
    "
    0.91
    ון
    0.91
     pamoja
    0.88
    Activations Density 0.002%

    No Known Activations