© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58209
    Prev
    Next
    INDEX
    Explanations

    special characters 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_11_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
     $
    0.86
     \
    0.81
     ge
    0.69
    0.69
                 
    0.66
     l
    0.66
    en
    0.66
     o
    0.66
     isn
    0.66
            
    0.65
    POSITIVE LOGITS
    íqu
    0.66
     fác
    0.63
    setChecked
    0.63
    が通販
    0.63
    昉
    0.63
    Sciences
    0.63
    "%(
    0.61
    ës
    0.58
    "</
    0.58
    ίας
    0.58
    Activations Density 0.000%

    No Known Activations