© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78633
    Prev
    Next
    INDEX
    Explanations

    leading to specific industry terms

    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_31_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
     viewport
    0.35
    Drake
    0.35
     averse
    0.35
    cion
    0.35
    quez
    0.34
    onter
    0.33
    illon
    0.32
    𝔀
    0.32
    नल
    0.32
    ड्र
    0.32
    POSITIVE LOGITS
     секре
    0.38
     найти
    0.36
    的网络
    0.36
     fij
    0.35
     ಮಹ
    0.35
     Surv
    0.35
    必須
    0.35
     ಹಿಂದೆ
    0.35
     ఆదేశ
    0.35
     deceit
    0.34
    Activations Density 0.002%

    No Known Activations