© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115931
    Prev
    Next
    INDEX
    Explanations

    your work / career

    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_27_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
     inconvén
    0.21
     这
    0.21
     내용을
    0.20
     বেশিরভাগ
    0.20
    ử
    0.19
     这是
    0.18
     দুই
    0.18
     ruining
    0.18
     Ferrara
    0.18
     Gregg
    0.18
    POSITIVE LOGITS
    Friday
    0.20
     माणूस
    0.19
    сона
    0.19
    лся
    0.19
    }(-\
    0.19
    نده
    0.18
    вая
    0.18
    Realistic
    0.18
    Neon
    0.18
     nests
    0.18
    Activations Density 0.000%

    No Known Activations