© 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. 200361
    Prev
    Next
    INDEX
    Explanations

    registered

    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
    Mask
    0.39
    cido
    0.39
     Pis
    0.39
    வின
    0.38
    jia
    0.38
    庙
    0.38
    ினார்கள்
    0.37
     S
    0.37
    মিক্যাল
    0.37
     मददगार
    0.37
    POSITIVE LOGITS
    NOWLED
    0.40
     conforms
    0.39
    粒
    0.38
    decorator
    0.36
    价
    0.36
    бата
    0.35
     Sext
    0.35
    egno
    0.35
    expects
    0.35
     distributor
    0.34
    Activations Density 0.000%

    No Known Activations