© 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. 199541
    Prev
    Next
    INDEX
    Explanations

    places

    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
    maxValue
    0.44
     दम
    0.40
    furnished
    0.40
    マ
    0.38
    ベ
    0.38
    lon
    0.38
    𝗟
    0.37
     Kc
    0.37
    <0x90>
    0.37
     tit
    0.37
    POSITIVE LOGITS
     Spencer
    0.44
    Spencer
    0.40
     Рим
    0.38
    Rome
    0.38
    Від
    0.38
    Spr
    0.36
     spiller
    0.36
    锼
    0.36
     Rome
    0.35
    Europe
    0.35
    Activations Density 0.006%

    No Known Activations