© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53023
    Prev
    Next
    INDEX
    Explanations

    spoke, exclaimed, declared, admitted

    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_31_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
     CLT
    0.40
     outweigh
    0.39
     Calvert
    0.39
     Elders
    0.38
     Transplantation
    0.37
     Pess
    0.37
     labor
    0.36
    󠁮
    0.36
     elders
    0.35
     internals
    0.35
    POSITIVE LOGITS
    :"))
    0.38
    并在
    0.38
    થે
    0.38
     并
    0.38
     beo
    0.38
    dek
    0.37
    并将
    0.37
     చెబు
    0.37
    тельской
    0.37
    ileged
    0.37
    Activations Density 0.008%

    No Known Activations