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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63278
    Prev
    Next
    INDEX
    Explanations

    synonym and thesaurus suggestions

    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_41_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
    ቲክ
    0.37
    অতি
    0.37
     ইনফ
    0.36
    Kayak
    0.36
    كب
    0.35
    应对
    0.35
    Loose
    0.35
    꼰
    0.35
    Attend
    0.35
    ణా
    0.34
    POSITIVE LOGITS
     thes
    1.45
     Thes
    1.41
     synonym
    1.24
     synonyms
    1.17
     Synonym
    1.17
    Syn
    1.02
    syn
    1.01
     synonymous
    0.98
     Syn
    0.97
     syn
    0.83
    Activations Density 0.015%

    No Known Activations