© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7291
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_40_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
    -​
    0.41
    ־
    0.38
    −
    0.35
    
    0.33
    ‐
    0.33
     Versus
    0.33
    ‑
    0.32
    –
    0.31
    -\\
    0.30
     versus
    0.30
    POSITIVE LOGITS
     الحد
    0.26
    翩
    0.25
     DELL
    0.25
     demikian
    0.24
    ാണ
    0.24
    ีย์
    0.24
     activ
    0.23
     wel
    0.23
     جول
    0.23
     MDLVertex
    0.23
    Activations Density 0.066%

    No Known Activations