© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154719
    Prev
    Next
    INDEX
    Explanations

    php array syntax

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    сть
    0.48
     സ്‌
    0.45
    ✞
    0.44
     سك
    0.44
    Star
    0.43
     देने
    0.42
    Intern
    0.38
     piede
    0.38
    㑨
    0.37
    暑
    0.37
    POSITIVE LOGITS
     fourth
    0.44
     underpinned
    0.43
     when
    0.42
     encroachment
    0.42
     pored
    0.41
     inspiring
    0.41
     जेव्हा
    0.41
     disks
    0.41
     interference
    0.40
     tapping
    0.40
    Activations Density 0.000%

    No Known Activations