© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33678
    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
    Г
    0.47
    -',
    0.37
     Tanah
    0.37
     masses
    0.36
    )—
    0.36
    awai
    0.36
     Palmer
    0.35
     massa
    0.35
    かっこ
    0.35
     tanah
    0.34
    POSITIVE LOGITS
     Antenna
    0.41
     Assertion
    0.41
     antenna
    0.41
     সুইস
    0.40
     antennae
    0.40
    夹
    0.39
    antenna
    0.39
     최대
    0.38
     Jerseys
    0.38
     ادي
    0.38
    Activations Density 0.004%

    No Known Activations