© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206466
    Prev
    Next
    INDEX
    Explanations

    Llama versions and parameters

    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_46_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
     instalar
    0.40
     स्टोर
    0.39
     αδ
    0.38
     Publish
    0.38
    琰
    0.38
     Mard
    0.37
     installieren
    0.37
    ▮
    0.37
     واب
    0.36
     Lol
    0.36
    POSITIVE LOGITS
     изу
    0.40
    开放
    0.40
    グラス
    0.38
     GTP
    0.38
     Syllabus
    0.37
     সাম্প্রদায়িক
    0.37
     asc
    0.36
    >);
    0.36
    стное
    0.36
     meditation
    0.35
    Activations Density 0.009%

    No Known Activations