© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30181
    Prev
    Next
    INDEX
    Explanations

    equivalence and relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     redis
    0.41
     BU
    0.38
     respons
    0.38
    covariant
    0.38
    杖
    0.37
    โอกาส
    0.37
     Redis
    0.37
     neglected
    0.36
    メリ
    0.36
    념
    0.36
    POSITIVE LOGITS
     equivalence
    0.61
    equivalence
    0.59
    Equ
    0.57
    equival
    0.57
     Equival
    0.57
     equival
    0.55
     Equ
    0.55
    Relation
    0.51
     relation
    0.51
    Sem
    0.50
    Activations Density 0.059%

    No Known Activations