© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33840
    Prev
    Next
    INDEX
    Explanations

    Verilog/code `begin`

    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
     Voting
    0.20
    偐
    0.19
     руб
    0.19
     एनी
    0.18
     थो
    0.18
     ź
    0.18
     institucional
    0.18
     Explos
    0.17
     hecha
    0.17
     Authorities
    0.17
    POSITIVE LOGITS
     remed
    0.19
    azas
    0.18
    awai
    0.18
    ätt
    0.17
     mourning
    0.17
    थर
    0.17
     Pelt
    0.17
    喆
    0.16
    㕸
    0.16
     fasting
    0.16
    Activations Density 0.000%

    No Known Activations