© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232695
    Prev
    Next
    INDEX
    Explanations

    associations

    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_46_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
     військо
    0.45
    воен
    0.40
    变
    0.40
    军
    0.38
     జి
    0.37
    军事
    0.36
     logout
    0.35
    പ്ര
    0.35
     عش
    0.35
    ()+"
    0.35
    POSITIVE LOGITS
    協會
    0.47
     associations
    0.46
     pipa
    0.46
    Association
    0.45
     Associations
    0.44
     tach
    0.44
    Associations
    0.43
    associations
    0.43
     association
    0.43
    association
    0.43
    Activations Density 0.000%

    No Known Activations