© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36621
    Prev
    Next
    INDEX
    Explanations

    Job

    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_50_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
    Houses
    0.45
    Gc
    0.40
    gian
    0.38
    Cele
    0.38
    replication
    0.38
    阂
    0.37
    lyrics
    0.37
    沐
    0.37
    acres
    0.37
    MCs
    0.36
    POSITIVE LOGITS
    кия
    0.45
     Precip
    0.44
    𝔀
    0.42
     रिव्यू
    0.38
     precipitate
    0.38
     Nec
    0.38
    ursor
    0.37
     trabalhar
    0.37
     рабочего
    0.37
     Jar
    0.37
    Activations Density 0.000%

    No Known Activations