© 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. 159187
    Prev
    Next
    INDEX
    Explanations

    "-ing" suffix

    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
    徠
    0.41
    picode
    0.40
     Pots
    0.40
     جوجل
    0.39
     marquee
    0.39
    Leaks
    0.38
    چ
    0.38
     Sonny
    0.37
    जगी
    0.37
    씰
    0.37
    POSITIVE LOGITS
    xpath
    0.44
    ermak
    0.44
     xpath
    0.37
    ulos
    0.36
    ንድ
    0.36
     overlooking
    0.36
     abord
    0.35
     unfolding
    0.35
     అధ్యక్ష
    0.35
    oods
    0.35
    Activations Density 0.000%

    No Known Activations