© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117623
    Prev
    Next
    INDEX
    Explanations

    that leads to

    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_27_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
     archae
    0.31
    σίας
    0.30
     მას
    0.29
     VIT
    0.29
    ুত
    0.28
    科學
    0.28
    θρω
    0.28
    잿
    0.28
     which
    0.28
     PREMIUM
    0.27
    POSITIVE LOGITS
    ave
    0.29
    Ia
    0.28
    wirkung
    0.27
    ย์
    0.27
    Always
    0.26
    dat
    0.25
     面
    0.25
    Time
    0.25
    लील
    0.25
     emphasis
    0.25
    Activations Density 0.007%

    No Known Activations