© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208176
    Prev
    Next
    INDEX
    Explanations

    CartPole, tic-tac-toe, bird, breakout

    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_19_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
     miliardi
    0.22
    䏲
    0.21
     imprison
    0.20
     миллиар
    0.20
    ОВО
    0.20
     pariy
    0.19
    ОР
    0.19
     millioner
    0.19
    МИ
    0.19
     petroleum
    0.19
    POSITIVE LOGITS
    size
    0.24
     Heights
    0.22
    self
    0.22
    g
    0.22
    ie
    0.21
    ky
    0.20
    height
    0.20
    S
    0.20
    set
    0.20
    use
    0.20
    Activations Density 0.002%

    No Known Activations