© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16571
    Prev
    Next
    INDEX
    Explanations

    proper one

    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
     ઘટ
    0.48
     dignitaries
    0.45
     mishaps
    0.44
     ailments
    0.43
    ഹാ
    0.43
     partake
    0.43
    袈
    0.42
     upkeep
    0.41
     القيم
    0.41
     কপি
    0.39
    POSITIVE LOGITS
    蛳
    0.44
    innamon
    0.41
     Yeah
    0.39
    icollis
    0.38
    Yeah
    0.38
     yeah
    0.36
    шинство
    0.36
    smouth
    0.36
     conversely
    0.35
     creature
    0.34
    Activations Density 0.039%

    No Known Activations