© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168821
    Prev
    Next
    INDEX
    Explanations

    special formatting elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     étant
    0.46
     Being
    0.45
    Being
    0.43
     visitors
    0.42
     করেনি
    0.42
    呵
    0.42
     পাবে
    0.41
     traff
    0.41
     পায়নি
    0.41
     BEING
    0.40
    POSITIVE LOGITS
    ND
    0.38
    pul
    0.37
    Dart
    0.37
    ана
    0.36
     &
    0.36
    анд
    0.36
    an
    0.36
    ,
    0.36
    х
    0.36
    左
    0.36
    Activations Density 0.000%

    No Known Activations