© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130786
    Prev
    Next
    INDEX
    Explanations

    time

    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_50_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
    con
    0.38
    argon
    0.38
    argc
    0.38
    溶
    0.37
    𝙷
    0.37
    ोत
    0.37
    alysis
    0.37
    itale
    0.37
     Pluto
    0.37
    َح
    0.36
    POSITIVE LOGITS
     trai
    0.38
     evolves
    0.38
     সত্ত্বেও
    0.38
    Frankreich
    0.38
     augmenting
    0.37
     हिंदु
    0.37
     cytochrome
    0.37
     minimising
    0.36
     Substituting
    0.36
     replying
    0.36
    Activations Density 0.001%

    No Known Activations