© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215764
    Prev
    Next
    INDEX
    Explanations

    why you

    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_31_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
    luck
    0.43
    রক্ষ
    0.38
     шрифт
    0.37
     وخت
    0.37
    lucky
    0.37
    ਦ
    0.36
     Oli
    0.36
     باد
    0.36
    幸运
    0.36
    នា
    0.36
    POSITIVE LOGITS
    טית
    0.42
     allow
    0.40
     welcoming
    0.39
     invasive
    0.39
    詹
    0.39
     permit
    0.38
     backyard
    0.38
    allow
    0.38
     studying
    0.38
     Allow
    0.37
    Activations Density 0.002%

    No Known Activations