© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3790
    Prev
    Next
    INDEX
    Explanations

    medical and research

    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_44_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
     swallow
    1.49
     Swallow
    1.45
     swallowed
    1.39
     swallowing
    1.39
    Sw
    1.13
     Sw
    1.10
    吞
    1.09
     sw
    1.08
     Swal
    1.05
    sw
    1.03
    POSITIVE LOGITS
     തീ
    0.42
     ತುಂಬಾ
    0.39
    疖
    0.39
    Running
    0.39
    串
    0.39
    சூ
    0.38
     दाह
    0.38
     Skins
    0.37
     Play
    0.37
    }=[
    0.36
    Activations Density 0.024%

    No Known Activations