© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117269
    Prev
    Next
    INDEX
    Explanations

    couple having or planning children

    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_27_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
     sheds
    0.38
     наоборот
    0.36
    凌
    0.35
     shedding
    0.35
    nows
    0.35
    यू
    0.34
     हां
    0.33
     Barang
    0.33
     =>
    0.33
     будь
    0.33
    POSITIVE LOGITS
     Kamp
    0.39
     স্বায়
    0.37
     kamp
    0.34
    飴
    0.33
    yst
    0.33
    াপি
    0.33
    厶
    0.33
    thione
    0.32
    󠁣
    0.32
     VALLEY
    0.32
    Activations Density 0.000%

    No Known Activations