© 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. 49356
    Prev
    Next
    INDEX
    Explanations

    hosts: and agent:

    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
    onclick
    0.38
     exs
    0.37
    生活的
    0.35
     opera
    0.34
     follows
    0.34
     فس
    0.34
    恐怖
    0.34
     त
    0.34
    ्या
    0.34
     prih
    0.34
    POSITIVE LOGITS
     потребуется
    0.39
    يزات
    0.38
     Mhm
    0.37
    ಧಾರ
    0.37
     dilat
    0.36
    ান্য
    0.36
     benötigen
    0.36
     Divid
    0.36
    unternehmen
    0.35
    αιο
    0.35
    Activations Density 0.001%

    No Known Activations