© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232893
    Prev
    Next
    INDEX
    Explanations

    between positions or spaces

    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_32_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
    торая
    0.38
    ➧
    0.38
    КС
    0.37
     toplant
    0.36
     pomiędzy
    0.36
    zwischen
    0.36
    ның
    0.36
    䍘
    0.35
    ᐳ
    0.35
    
    0.35
    POSITIVE LOGITS
     Coloring
    0.44
     регули
    0.38
     Meanwhile
    0.38
     coloring
    0.37
    tokenize
    0.36
     Handwritten
    0.35
    éré
    0.34
     ಆದರೆ
    0.34
     পৌর
    0.33
     resize
    0.33
    Activations Density 0.002%

    No Known Activations