© 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. 35710
    Prev
    Next
    INDEX
    Explanations

    numbers and 'k' or 'K'

    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
     فتح
    0.45
     डिप्ट
    0.44
    刄
    0.43
     нарушение
    0.41
     اطلاع
    0.40
    屒
    0.40
     سبيل
    0.39
    कोष्ठ
    0.39
     argc
    0.38
    罾
    0.38
    POSITIVE LOGITS
     treas
    0.48
    Va
    0.40
    treas
    0.39
     na
    0.38
    ks
    0.38
    ¶
    0.37
    exams
    0.37
    Je
    0.36
    Treas
    0.36
     VA
    0.35
    Activations Density 0.000%

    No Known Activations