© 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. 133735
    Prev
    Next
    INDEX
    Explanations

    melanin

    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
     Bühne
    0.42
     scompar
    0.40
     บุ
    0.39
    ਼
    0.39
    anch
    0.39
     thở
    0.37
     ကု
    0.36
     Thacker
    0.36
    hame
    0.36
    ᄄ
    0.36
    POSITIVE LOGITS
    ographs
    0.43
     REN
    0.40
     Nom
    0.39
     Rens
    0.38
    attan
    0.38
     Alexis
    0.37
    TTLE
    0.37
    謄
    0.37
    TT
    0.37
    qst
    0.37
    Activations Density 0.000%

    No Known Activations