© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9480
    Prev
    Next
    INDEX
    Explanations

    composition of things

    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
    ین
    0.25
    ۰
    0.21
    SA
    0.19
    azioni
    0.19
     вообще
    0.19
    Re
    0.19
    no
    0.18
    گی
    0.18
     antara
    0.18
    ]][
    0.17
    POSITIVE LOGITS
     Rauch
    0.20
     militias
    0.19
    ぬい
    0.19
     commemorates
    0.19
     fossils
    0.19
    ルド
    0.19
     contemplates
    0.19
     itemView
    0.19
     Nashville
    0.19
     ambitions
    0.19
    Activations Density 0.004%

    No Known Activations