© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 21831
    Prev
    Next
    INDEX
    Explanations

    continuation or ellipsis

    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_56_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
    </b>
    0.41
    ্যানের
    0.36
    </h3>
    0.36
     জনগোষ্ঠীর
    0.35
    㗁
    0.35
    㴼
    0.33
    atrième
    0.33
    ֨
    0.32
     inverses
    0.31
     \&
    0.31
    POSITIVE LOGITS
    <eos>
    2.27
     […]
    1.05
    […]
    0.92
    ៕
    0.79
    Continue
    0.68
     继续访问
    0.62
     [...]
    0.58
    <unused61>
    0.57
    <unused63>
    0.57
    [...]
    0.57
    Activations Density 0.239%

    No Known Activations