© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176455
    Prev
    Next
    INDEX
    Explanations

    heat pumps

    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_24_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
    ois
    0.41
     mRNA
    0.40
     mice
    0.37
     scriptures
    0.37
     ramb
    0.36
    ත
    0.36
     Circuits
    0.36
     claws
    0.36
     plasma
    0.35
    ivos
    0.35
    POSITIVE LOGITS
    埇
    0.48
     بالنسبة
    0.41
    AddField
    0.40
    ારે
    0.40
     مناسب
    0.40
    媝
    0.40
    <0x1C>
    0.39
    媢
    0.39
     ابنائي
    0.39
     उचित
    0.38
    Activations Density 0.000%

    No Known Activations