© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252463
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
    屿
    0.39
     '!
    0.38
    eq
    0.36
    ETO
    0.35
    ='+
    0.34
    ddots
    0.34
     Hint
    0.33
    +"/
    0.33
    carpet
    0.33
    ревнования
    0.33
    POSITIVE LOGITS
    ംഗ
    0.44
    䊂
    0.43
     making
    0.40
     régi
    0.40
     বর্তমান
    0.39
     PF
    0.39
    λλά
    0.39
    ümer
    0.38
     kitten
    0.38
    umon
    0.37
    Activations Density 0.001%

    No Known Activations