© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81881
    Prev
    Next
    INDEX
    Explanations

    semantic role labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    at
    1.63
    ਰ
    1.48
    સ
    1.40
     the
    1.39
     not
    1.36
    d
    1.31
     όχι
    1.29
    ی
    1.24
    am
    1.23
    ਮ
    1.22
    POSITIVE LOGITS
    -
    1.24
    كار
    1.19
    يل
    1.15
    ુ
    1.08
    ני
    1.06
    ต์
    1.06
    ك
    1.05
    、
    1.05
    מית
    1.04
    meler
    1.02
    Activations Density 0.002%

    No Known Activations