© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115787
    Prev
    Next
    INDEX
    Explanations

    members of groups

    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
     ultrast
    0.34
     ಬರ
    0.33
     മിക
    0.33
     siècle
    0.33
     physicality
    0.32
     Coaching
    0.32
     भक्ति
    0.32
    漃
    0.32
    欸
    0.31
     utilising
    0.31
    POSITIVE LOGITS
    Forgot
    0.37
    Members
    0.36
     камера
    0.34
    Dollar
    0.34
    Danny
    0.33
     anggota
    0.33
    ताल
    0.33
    Candy
    0.32
     miembros
    0.32
    สมาชิก
    0.32
    Activations Density 0.002%

    No Known Activations