© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9632
    Prev
    Next
    INDEX
    Explanations

    split into sub-words

    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_13_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
     način
    0.63
     dó
    0.56
     Акысыз
    0.51
    y
    0.51
    
    0.50
    koliko
    0.49
    पोर्ट
    0.48
     ойнотуу
    0.48
     اکس
    0.48
     l
    0.46
    POSITIVE LOGITS
    ε
    0.59
    arp
    0.55
    <b>
    0.54
    oder
    0.53
    und
    0.52
     two
    0.50
    ार्ड
    0.50
    \
    0.50
    aux
    0.49
     तय
    0.49
    Activations Density 0.043%

    No Known Activations