© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204909
    Prev
    Next
    INDEX
    Explanations

    changes, refurbishment, sciences

    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
     }}^{
    0.17
     Delaware
    0.17
     کشورهای
    0.17
     Amherst
    0.16
     জানাচ্ছেন
    0.16
     Azerbaijan
    0.15
     Colorado
    0.15
     Congressional
    0.15
     succumbed
    0.15
     interviews
    0.15
    POSITIVE LOGITS
     tén
    0.21
    辇
    0.20
    мога
    0.19
    жеб
    0.19
     servos
    0.19
     tém
    0.18
     contrace
    0.18
     zh
    0.18
     overwrite
    0.18
     szolg
    0.18
    Activations Density 0.001%

    No Known Activations