© 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. 66231
    Prev
    Next
    INDEX
    Explanations

    java

    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
    amo
    0.45
     gr
    0.43
    rio
    0.42
    g
    0.42
     Blackmore
    0.42
     sid
    0.41
    url
    0.40
    amt
    0.40
     gone
    0.39
    ingo
    0.39
    POSITIVE LOGITS
    탁
    0.42
    कोप
    0.39
     Ipsum
    0.39
    䡊
    0.39
    უნქ
    0.38
    jení
    0.37
    σει
    0.37
    elje
    0.37
    ತೆ
    0.37
    ]")]
    0.36
    Activations Density 0.001%

    No Known Activations