© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117475
    Prev
    Next
    INDEX
    Explanations

    use of, use at

    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
    𝖓
    0.40
     Cardano
    0.37
     далее
    0.34
    𝔱
    0.32
     中心
    0.32
     ((*
    0.32
    ttps
    0.31
    僕は
    0.31
    转载
    0.31
     Coding
    0.31
    POSITIVE LOGITS
    ogran
    0.31
     takže
    0.31
    。
    0.30
    खों
    0.30
     duas
    0.30
    current
    0.29
     уче
    0.29
    CSF
    0.29
     verst
    0.28
    onzo
    0.28
    Activations Density 0.007%

    No Known Activations