© 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. 116755
    Prev
    Next
    INDEX
    Explanations

    aaoraadiarrheaproperties

    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
    лари
    0.45
    विषयी
    0.41
     уж
    0.40
    现实
    0.40
     داریم
    0.39
     iskol
    0.39
    ˑ
    0.39
    欵
    0.39
    itett
    0.39
     कर्ज
    0.38
    POSITIVE LOGITS
     herein
    0.43
     nul
    0.42
     thereof
    0.42
    nostic
    0.42
     incorporates
    0.40
     net
    0.39
     netting
    0.39
     acoustic
    0.39
     comprises
    0.38
    gross
    0.38
    Activations Density 0.000%

    No Known Activations