© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11710
    Prev
    Next
    INDEX
    Explanations

    under development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    Containers
    0.40
     Them
    0.38
     ముందు
    0.37
    นุ
    0.37
     Մ
    0.37
     zlep
    0.37
     क्वे
    0.37
     ними
    0.36
    牡丹
    0.36
     muebles
    0.36
    POSITIVE LOGITS
     incorporation
    0.38
     embracing
    0.38
    诏
    0.37
     schal
    0.36
     <=
    0.36
     occasion
    0.36
    Ig
    0.36
     knocking
    0.35
     segu
    0.35
    ёл
    0.35
    Activations Density 0.037%

    No Known Activations