© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217014
    Prev
    Next
    INDEX
    Explanations

    Mumbai, India, capital

    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
    urat
    0.42
     Bhajan
    0.39
    诵
    0.36
     ICT
    0.36
     நூற்ற
    0.36
     주기
    0.36
    jahter
    0.35
     Mbps
    0.35
     Tik
    0.35
    夜
    0.34
    POSITIVE LOGITS
     ships
    0.40
     anlay
    0.39
     posi
    0.38
    тала
    0.38
    łów
    0.37
     желания
    0.37
     opinions
    0.36
     мнению
    0.36
    lnk
    0.35
     simonsen
    0.35
    Activations Density 0.000%

    No Known Activations