© 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. 253955
    Prev
    Next
    INDEX
    Explanations

    7

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pus
    0.41
     terms
    0.39
     আনুগত্য
    0.35
     prop
    0.35
    athy
    0.34
    ╔
    0.34
     skil
    0.34
    Recognizer
    0.33
    ምና
    0.33
    terms
    0.33
    POSITIVE LOGITS
     ৬
    0.45
    ６
    0.44
     ६
    0.43
    ๖
    0.43
    <0xB2>
    0.41
    ៦
    0.40
     ஆறு
    0.39
    ዬ
    0.39
     zomer
    0.38
     ছয়
    0.38
    Activations Density 0.001%

    No Known Activations