© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44870
    Prev
    Next
    INDEX
    Explanations

    impl keyword implementations

    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
     πληροφο
    0.56
    »
    0.56
     Teilen
    0.55
    ?");
    0.55
    ()}
    0.52
     chamado
    0.52
    資訊
    0.51
    ília
    0.51
     настоя
    0.51
    𝘖
    0.50
    POSITIVE LOGITS
    derived
    0.63
    er
    0.63
     =
    0.57
     Heir
    0.56
    nici
    0.55
    ার
    0.55
    canic
    0.51
     است
    0.51
    㵄
    0.51
    anten
    0.50
    Activations Density 0.001%

    No Known Activations