© 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. 16504
    Prev
    Next
    INDEX
    Explanations

    action verbs following connecting words

    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
    trace
    0.31
     calculation
    0.30
    सात
    0.29
     dard
    0.28
    ])):
    0.28
     sk
    0.27
     நியூ
    0.27
     basın
    0.27
     sente
    0.27
    sees
    0.27
    POSITIVE LOGITS
     derived
    0.31
    砥
    0.29
     treating
    0.28
     enunci
    0.28
     handbook
    0.27
     extracted
    0.26
     identified
    0.26
     Extract
    0.26
     Derived
    0.25
    ജ്
    0.25
    Activations Density 0.059%

    No Known Activations