© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52226
    Prev
    Next
    INDEX
    Explanations

    _

    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_30_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
     похађа
    0.38
     для
    0.34
     DETERMIN
    0.34
     কারফিউ
    0.32
     برای
    0.31
     entweder
    0.30
     بتر
    0.30
    켤
    0.30
     याच
    0.29
     துரு
    0.29
    POSITIVE LOGITS
    green
    0.33
     arrows
    0.33
    lt
    0.32
     green
    0.31
    aint
    0.29
     intensity
    0.29
     Keith
    0.29
    crown
    0.29
    sports
    0.29
    right
    0.28
    Activations Density 0.001%

    No Known Activations