© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7056
    Prev
    Next
    INDEX
    Explanations

    principle of least privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     音
    0.35
    音が
    0.35
    聲
    0.35
     giọng
    0.33
     británico
    0.33
     বান্ধ
    0.32
     صوت
    0.32
    acé
    0.32
     ശബ്
    0.32
     କରି
    0.31
    POSITIVE LOGITS
    权的
    0.35
    ỡ
    0.34
     authorize
    0.33
     मेड
    0.32
     Schne
    0.32
     approve
    0.31
    ("***
    0.31
    ཐ
    0.31
     standing
    0.31
    Agree
    0.31
    Activations Density 0.007%

    No Known Activations