© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24860
    Prev
    Next
    INDEX
    Explanations

    punctuation or delimiters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     বলিয়
    0.38
    由此
    0.35
     exemplify
    0.33
    ারিং
    0.32
     Besides
    0.31
     পদ্ধতিতে
    0.30
    𒇷
    0.30
    氤
    0.30
    торы
    0.30
    ্তার
    0.30
    POSITIVE LOGITS
    -"
    1.78
     :-
    1.64
    -”
    1.63
    -\
    1.62
    -.
    1.61
    -)
    1.61
    -,
    1.59
     -"
    1.55
    -(
    1.55
    -'
    1.55
    Activations Density 0.072%

    No Known Activations