© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50927
    Prev
    Next
    INDEX
    Explanations

    nearby

    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_30_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
    arantad
    0.41
     cuándo
    0.39
     केंद
    0.39
    क्रेट
    0.38
    两者
    0.38
    侣
    0.37
    tbLabel
    0.37
    ണ്ഡി
    0.37
    出去
    0.36
     жүктөө
    0.36
    POSITIVE LOGITS
    _\
    0.41
     petitions
    0.38
     keeps
    0.37
     undergoes
    0.36
    %>%
    0.36
     Tapat
    0.36
     Oft
    0.35
     from
    0.35
     promotes
    0.35
     Gets
    0.35
    Activations Density 0.002%

    No Known Activations