© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59570
    Prev
    Next
    INDEX
    Explanations

    type of classifier

    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_11_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
     The
    0.33
    st
    0.32
    hill
    0.31
    v
    0.30
    t
    0.30
    dann
    0.29
     hinder
    0.29
    d
    0.29
    sthe
    0.29
    al
    0.28
    POSITIVE LOGITS
     dolphins
    0.34
    ف
    0.34
     objetos
    0.34
     apartamentos
    0.34
     vuelos
    0.33
    ол
    0.32
    ມ
    0.32
     baterías
    0.32
    𝘮
    0.32
     kilomètres
    0.31
    Activations Density 0.033%

    No Known Activations