© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14088
    Prev
    Next
    INDEX
    Explanations

    discussing future or conditional

    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
    IP
    0.34
     nếu
    0.33
     đình
    0.33
    如果是
    0.33
    IL
    0.32
    Jika
    0.32
    ］
    0.32
    奘
    0.32
    墮
    0.32
    酆
    0.32
    POSITIVE LOGITS
    ку
    0.38
     С
    0.35
    aly
    0.35
    w
    0.33
    rs
    0.33
     RSM
    0.32
     бро
    0.32
     S
    0.32
     M
    0.31
     rep
    0.31
    Activations Density 0.216%

    No Known Activations