© 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. 132687
    Prev
    Next
    INDEX
    Explanations

    specific names and things

    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
     كا
    0.40
     خمسه
    0.39
    衹
    0.38
     อ่า
    0.38
    Ｄ
    0.37
    菀
    0.37
     الحديث
    0.37
    辂
    0.36
    ıldığı
    0.36
    ಋ
    0.36
    POSITIVE LOGITS
    iger
    0.45
    ¯</
    0.44
     Mata
    0.44
     वायर
    0.43
    ayout
    0.42
    Connor
    0.42
    zoni
    0.41
    TGF
    0.41
    Bere
    0.40
    Cursor
    0.39
    Activations Density 0.004%

    No Known Activations