© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203809
    Prev
    Next
    INDEX
    Explanations

    settlements

    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
     pegged
    0.37
    ützen
    0.36
    ్రహ
    0.36
    峦
    0.35
     غرفة
    0.35
     thóc
    0.34
    ósito
    0.34
     frameN
    0.34
    妄
    0.34
    のではないでしょうか
    0.34
    POSITIVE LOGITS
     settlement
    1.96
     settlements
    1.91
     Settlement
    1.70
     Settlements
    1.69
    Sett
    1.52
    sett
    1.42
     settle
    1.41
     settled
    1.35
     settles
    1.31
     settling
    1.30
    Activations Density 0.002%

    No Known Activations