© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36605
    Prev
    Next
    INDEX
    Explanations

    code and github

    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
     recib
    0.47
    휠
    0.41
     Knock
    0.40
     PWM
    0.39
     uncoated
    0.38
     অক্ষম
    0.38
     Strecke
    0.38
     backyard
    0.38
     received
    0.37
     Koy
    0.37
    POSITIVE LOGITS
    randint
    0.38
    ждение
    0.38
    дание
    0.38
    <0xBD>
    0.37
    ুদ্ধ
    0.37
    editText
    0.36
    вобо
    0.36
     Belling
    0.36
    助手
    0.36
    ͆
    0.36
    Activations Density 0.007%

    No Known Activations