© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 204389
    Prev
    Next
    INDEX
    Explanations

    offer a friend

    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_46_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
     Merchandise
    0.45
    SequentialGroup
    0.40
     드
    0.40
     weird
    0.39
     Protest
    0.38
    expl
    0.36
    .([]
    0.36
     怪
    0.36
     बिल्कुल
    0.36
     nai
    0.35
    POSITIVE LOGITS
    DE
    0.45
    De
    0.38
     medición
    0.38
    Size
    0.37
    Tot
    0.36
     DE
    0.36
    Newton
    0.36
    Teams
    0.36
    wert
    0.35
    áss
    0.35
    Activations Density 0.001%

    No Known Activations