© 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. 200796
    Prev
    Next
    INDEX
    Explanations

    historical dates

    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
    Portrait
    0.33
    ocke
    0.33
    ose
    0.33
    scapes
    0.33
    ocer
    0.33
    enti
    0.32
    -
    0.32
    Cult
    0.32
     δυ
    0.32
    Bitmap
    0.31
    POSITIVE LOGITS
     affirmat
    0.40
    ❞
    0.39
    嬋
    0.39
    ೭
    0.38
    ulières
    0.36
    кы
    0.35
    सर्गिक
    0.35
    ๙
    0.35
     सना
    0.35
    COMANDA
    0.35
    Activations Density 0.005%

    No Known Activations