© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18727
    Prev
    Next
    INDEX
    Explanations

    Label

    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_15_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
     assimilation
    0.48
    ussions
    0.45
     coco
    0.45
     dissipation
    0.45
     imperfection
    0.44
     emphasis
    0.44
    ୟ
    0.44
     magnetization
    0.43
     diffusion
    0.43
    AMINATION
    0.42
    POSITIVE LOGITS
    V
    0.61
     Букмекер
    0.60
    ंबू
    0.58
     wharf
    0.57
    huge
    0.55
     Пла
    0.54
    vcx
    0.53
    v
    0.51
    ]?
    0.51
    haram
    0.50
    Activations Density 0.008%

    No Known Activations