© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204097
    Prev
    Next
    INDEX
    Explanations

    hopes dashed

    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
     expectation
    0.46
     penetration
    0.39
    Absorption
    0.38
    }{}
    0.37
     absorption
    0.36
    absorption
    0.36
     trapez
    0.36
     Penet
    0.36
     흡
    0.36
     చేయ
    0.36
    POSITIVE LOGITS
     môn
    0.40
     валю
    0.40
     শ্ব
    0.39
    ታዊ
    0.39
     सूचीबद्ध
    0.38
     Gallup
    0.38
    endale
    0.37
    ምት
    0.37
    unjukkan
    0.37
     Cura
    0.37
    Activations Density 0.002%

    No Known Activations