© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11875
    Prev
    Next
    INDEX
    Explanations

    affiliate, based, were

    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
     nosotros
    0.19
    V
    0.17
    reg
    0.16
    io
    0.16
    {
    0.16
    R
    0.16
    我们在
    0.16
    We
    0.16
     Dialogue
    0.16
    8
    0.15
    POSITIVE LOGITS
     કરશે
    0.15
    ूम
    0.14
    សំណ
    0.14
     accomplishes
    0.14
     фу
    0.14
    мести
    0.13
    𝕦
    0.13
    イ
    0.13
    ш
    0.13
    嗦
    0.13
    Activations Density 0.062%

    No Known Activations