© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164135
    Prev
    Next
    INDEX
    Explanations

    great circle distance

    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_13_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
    >
    0.46
     efeitos
    0.35
    TER
    0.34
    “
    0.34
    )
    0.33
     Seasonal
    0.33
    Ѡ
    0.33
     Porque
    0.32
    ନ
    0.32
    Precis
    0.32
    POSITIVE LOGITS
    াক্ত
    0.41
     cStart
    0.38
    বন্ধু
    0.36
     "?"]
    0.34
    ীকে
    0.34
    ุป
    0.34
    }}$;
    0.34
    াহত
    0.34
    球面
    0.33
    ులు
    0.33
    Activations Density 0.009%

    No Known Activations