© 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. 22810
    Prev
    Next
    INDEX
    Explanations

    cabinet

    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
     SA
    0.61
    SA
    0.56
    South
    0.54
     South
    0.54
    🇿
    0.50
     SOUTH
    0.47
     साउथ
    0.47
    南
    0.46
     Adelaide
    0.45
     capitals
    0.43
    POSITIVE LOGITS
     CD
    0.49
     cabinet
    0.47
     CDs
    0.41
     Cabinet
    0.41
     carte
    0.40
    CD
    0.40
     real
    0.39
    cabinet
    0.38
     कैबिनेट
    0.38
     salted
    0.37
    Activations Density 0.002%

    No Known Activations