© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14977
    Prev
    Next
    INDEX
    Explanations

    upgrade pip

    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_40_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
     setName
    0.43
    gore
    0.39
     frictionless
    0.39
    ޚ
    0.38
    ාව
    0.38
     ゴ
    0.38
    appName
    0.38
    "./
    0.38
     Rxd
    0.36
    ្ម
    0.36
    POSITIVE LOGITS
     Veer
    0.38
    DAN
    0.38
     nine
    0.38
    prompt
    0.38
     précie
    0.38
    Nine
    0.37
    "`
    0.36
    éndose
    0.36
     уйнау
    0.36
    Secret
    0.36
    Activations Density 0.003%

    No Known Activations