© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11745
    Prev
    Next
    INDEX
    Explanations

    set by creators or set aside

    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_40_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
    irim
    0.45
     Efforts
    0.40
    '>
    0.40
    माया
    0.39
     slimming
    0.38
     }}">
    0.38
    漱
    0.38
     Jiří
    0.38
    蓆
    0.37
     Lynn
    0.37
    POSITIVE LOGITS
     outwe
    0.46
    आउट
    0.44
     obtiene
    0.43
    Ла
    0.42
    OutSize
    0.41
     બહાર
    0.41
     SURVEY
    0.40
    Из
    0.40
    Out
    0.39
     out
    0.39
    Activations Density 0.090%

    No Known Activations