© 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. 216027
    Prev
    Next
    INDEX
    Explanations

    constraints

    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
    દાન
    0.41
    Denis
    0.40
     Denis
    0.38
     دن
    0.37
    romax
    0.35
     ద
    0.35
     Rox
    0.35
     दंग
    0.35
    CP
    0.34
     جا
    0.34
    POSITIVE LOGITS
    ्रिया
    0.44
     မှ
    0.41
     Stru
    0.40
     polling
    0.39
     constraint
    0.38
    Constr
    0.38
     sito
    0.38
    擇
    0.38
     inhib
    0.37
     constrain
    0.37
    Activations Density 0.001%

    No Known Activations