© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    +

    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
    ಮ
    0.41
     FIVE
    0.40
    Tras
    0.40
     scur
    0.40
     ৫০০
    0.39
    Five
    0.39
    ۵
    0.39
    ólogo
    0.38
     пять
    0.37
    setUrl
    0.37
    POSITIVE LOGITS
    щин
    0.41
    adav
    0.41
    लपुर
    0.38
    休
    0.38
    deployed
    0.36
    UBE
    0.35
    <0xB3>
    0.35
     IW
    0.34
     দৌ
    0.34
    libc
    0.34
    Activations Density 0.000%

    No Known Activations