© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198088
    Prev
    Next
    INDEX
    Explanations

    Abernathy, Armitage

    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_50_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
    zers
    0.49
    lés
    0.44
    纱
    0.42
    adies
    0.42
    itage
    0.40
    േഷൻ
    0.40
    lers
    0.39
    bert
    0.39
    chester
    0.38
     NPM
    0.38
    POSITIVE LOGITS
     ASE
    0.42
     موت
    0.39
    ភ្
    0.38
    鼹
    0.38
    Jimbo
    0.37
     motoc
    0.35
     translateY
    0.34
     гипсо
    0.33
    moh
    0.33
     ase
    0.33
    Activations Density 0.000%

    No Known Activations