© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175698
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    jav
    0.41
     pajama
    0.41
    apj
    0.40
    جا
    0.38
     Jacques
    0.38
    }|$
    0.37
    ख
    0.37
    łuż
    0.37
     दाता
    0.37
    财政
    0.37
    POSITIVE LOGITS
     टाइप्स
    0.41
    シル
    0.39
    ников
    0.39
     Anche
    0.39
    angkan
    0.38
    Victoria
    0.38
     Rhodes
    0.38
     イ
    0.38
    ົນ
    0.38
     Gent
    0.38
    Activations Density 0.009%

    No Known Activations