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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164956
    Prev
    Next
    INDEX
    Explanations

    3D modelling and rendering

    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_13_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
    ینڈ
    0.19
     entanglement
    0.18
     be
    0.18
     entitlement
    0.18
    ويلة
    0.18
    preview
    0.17
    rors
    0.17
    ሪ
    0.17
     entitle
    0.17
     out
    0.17
    POSITIVE LOGITS
    မဟုတ်
    0.21
     southbound
    0.21
     ostatnich
    0.20
     phthal
    0.20
     Scheme
    0.19
     таксама
    0.19
     больных
    0.19
     ถนน
    0.19
     ஜி
    0.19
     動画
    0.19
    Activations Density 0.008%

    No Known Activations