© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213570
    Prev
    Next
    INDEX
    Explanations

    purpose or avoidance

    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_47_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
    phil
    0.41
    ació
    0.41
     قابل
    0.41
    畐
    0.40
     केयर
    0.39
    ishment
    0.38
    ONA
    0.38
    rics
    0.37
    rence
    0.37
    udence
    0.37
    POSITIVE LOGITS
     ElevatedButton
    0.41
    酵素
    0.40
    刀
    0.38
     zapewn
    0.38
     Norwalk
    0.38
     ENS
    0.38
    ufficient
    0.38
     memastikan
    0.37
     room
    0.37
     performing
    0.37
    Activations Density 0.000%

    No Known Activations