© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48390
    Prev
    Next
    INDEX
    Explanations

    LD followed by specific characters or words

    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_10_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
    el
    1.28
    t
    1.13
    le
    0.96
     for
    0.93
     $
    0.88
    ت
    0.82
     $)
    0.81
    me
    0.79
    chmod
    0.77
     An
    0.75
    POSITIVE LOGITS
    ים
    1.35
    ні
    1.23
    ς
    1.23
    ের
    1.21
    s
    1.21
    ی
    1.16
    2
    1.08
    ি
    1.08
    ો
    1.07
    ا
    1.05
    Activations Density 0.004%

    No Known Activations