© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239018
    Prev
    Next
    INDEX
    Explanations

    higher or lower

    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_25_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
     Care
    0.26
     bottle
    0.26
     ভারসাম্য
    0.26
    上で
    0.26
    %',
    0.26
    ເພດ
    0.25
     database
    0.25
    Care
    0.25
     変
    0.25
     karna
    0.25
    POSITIVE LOGITS
    ICHIGAN
    0.27
    desa
    0.27
    HCR
    0.27
     १९
    0.26
    uuuu
    0.26
    باش
    0.26
     accomplish
    0.25
    🔥🔥
    0.25
    🪐
    0.25
    क्रम
    0.25
    Activations Density 0.002%

    No Known Activations