© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5372
    Prev
    Next
    INDEX
    Explanations

    still learning

    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_44_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
     encore
    0.39
    十二章
    0.39
     douze
    0.38
    ൂര്‍
    0.37
     confident
    0.36
    elé
    0.36
    leeve
    0.35
    媚
    0.35
    all
    0.35
    fill
    0.34
    POSITIVE LOGITS
     ब्रे
    0.36
    ቢ
    0.36
    缺
    0.36
     Continental
    0.36
     CMP
    0.36
     aft
    0.35
     லா
    0.35
     εξα
    0.35
     हजार
    0.35
     Brig
    0.35
    Activations Density 0.014%

    No Known Activations