© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50629
    Prev
    Next
    INDEX
    Explanations

    Principles

    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_55_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
     dependiendo
    0.43
    انہ
    0.41
     depending
    0.41
    ➢
    0.40
     introduce
    0.40
    표
    0.39
     используя
    0.38
     связано
    0.37
    ▼
    0.37
    introduce
    0.37
    POSITIVE LOGITS
    hing
    0.38
     faveur
    0.38
    Mist
    0.37
    hk
    0.37
    sects
    0.36
    getNumberOf
    0.36
     Lonely
    0.36
    のために
    0.36
    Kindly
    0.35
     Arag
    0.35
    Activations Density 0.018%

    No Known Activations