© 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. 198490
    Prev
    Next
    INDEX
    Explanations

    Name

    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
     Asphalt
    0.41
    òa
    0.39
    asilkan
    0.39
    <0x8B>
    0.37
    Pu
    0.37
     Synthesis
    0.37
     tak
    0.36
     так
    0.36
     কাছ
    0.36
     कोट
    0.36
    POSITIVE LOGITS
    libc
    0.49
    गम
    0.39
     libc
    0.38
    server
    0.38
    fontsize
    0.38
    ]".
    0.38
     männ
    0.37
    Бахар
    0.37
    ITER
    0.37
     dampen
    0.36
    Activations Density 0.000%

    No Known Activations