© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101723
    Prev
    Next
    INDEX
    Explanations

    lycopene

    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_14_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
     شاید
    0.53
    ars
    0.50
     paragraph
    0.49
    hibition
    0.49
     abduction
    0.48
     tanha
    0.48
     ظاهر
    0.48
    嫐
    0.47
    indo
    0.47
     عفوا
    0.46
    POSITIVE LOGITS
    疆
    0.54
    <0xE2>
    0.53
    ಿವ
    0.53
    кара
    0.52
     hearing
    0.52
     đường
    0.52
     Hearings
    0.51
    ﻒ
    0.51
    كال
    0.50
     Clín
    0.50
    Activations Density 0.001%

    No Known Activations