© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208794
    Prev
    Next
    INDEX
    Explanations

    data

    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_20_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
    istered
    0.26
     со
    0.24
     viszont
    0.23
    kében
    0.23
     wyją
    0.22
    mazing
    0.22
     стати
    0.22
    剪
    0.22
    fatter
    0.22
    intera
    0.22
    POSITIVE LOGITS
     familles
    0.27
     portraits
    0.25
    ⇀
    0.24
     آمد
    0.24
    0
    0.24
    ოგ
    0.24
     etch
    0.24
     gf
    0.23
    ικούς
    0.23
    Histoire
    0.23
    Activations Density 0.016%

    No Known Activations