© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66845
    Prev
    Next
    INDEX
    Explanations

    encoded or raw data

    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_51_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
     zwölf
    0.41
    ᠴ
    0.39
     ML
    0.38
    punch
    0.38
     forty
    0.38
     finalement
    0.37
    propertyName
    0.37
    ቻል
    0.37
     অধর
    0.36
     ጭ
    0.36
    POSITIVE LOGITS
     Gauss
    0.40
    inska
    0.38
    ixa
    0.38
     תק
    0.38
    arka
    0.38
    abr
    0.37
     Heav
    0.37
     gauss
    0.37
    valid
    0.36
    helle
    0.36
    Activations Density 0.000%

    No Known Activations