© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85718
    Prev
    Next
    INDEX
    Explanations

    factual accuracy

    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_18_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
    జే
    0.24
    AssetDiscovery
    0.23
    cU
    0.22
    甴
    0.22
    Вакансия
    0.21
    charge
    0.21
    foot
    0.21
    blest
    0.21
     kojoj
    0.21
    ][]
    0.20
    POSITIVE LOGITS
     гаранти
    0.23
     defines
    0.20
     improves
    0.20
     aumentar
    0.20
     surpasses
    0.19
     zvyš
    0.19
     guarantees
    0.19
     garantizar
    0.18
     совмести
    0.18
     aumentare
    0.18
    Activations Density 0.010%

    No Known Activations