© 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. 31308
    Prev
    Next
    INDEX
    Explanations

    places

    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
    श्विक
    0.43
     सेन
    0.42
    CIRCLE
    0.41
    Kah
    0.41
    Ba
    0.40
     Ignite
    0.40
    寶
    0.40
    Circle
    0.39
    Bah
    0.39
    bah
    0.39
    POSITIVE LOGITS
     Norweg
    0.38
     warping
    0.37
    oppers
    0.37
     Megan
    0.36
     रिप्रोड
    0.36
    uali
    0.36
    рожден
    0.36
    сү
    0.36
     O
    0.35
    rose
    0.35
    Activations Density 0.001%

    No Known Activations