© 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. 121221
    Prev
    Next
    INDEX
    Explanations

    3

    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
    ֜
    0.44
    結局
    0.42
    Eventually
    0.38
    rokken
    0.38
    
    0.38
    Ꮐ
    0.38
    জের
    0.37
    에도
    0.37
    陼
    0.37
     techs
    0.36
    POSITIVE LOGITS
    StreetMap
    0.41
     Walk
    0.41
     Scouting
    0.38
     walk
    0.37
     op
    0.36
    艳
    0.35
     Visit
    0.35
     Field
    0.35
     aast
    0.34
     přes
    0.34
    Activations Density 0.000%

    No Known Activations