© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237273
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    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_25_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
    akarta
    0.39
     특히
    0.38
     즉
    0.37
    فرج
    0.37
     embankment
    0.37
    atma
    0.36
    Lub
    0.36
     alterna
    0.36
    أم
    0.36
     Multif
    0.36
    POSITIVE LOGITS
     genotypes
    0.36
    Conventional
    0.36
    ங்களிலிருந்து
    0.35
    ရောက်
    0.35
    jek
    0.34
    饮食
    0.34
    成年
    0.33
    ม
    0.33
    肠
    0.33
    کسی
    0.32
    Activations Density 0.010%

    No Known Activations