© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61065
    Prev
    Next
    INDEX
    Explanations

    NPR, DPRK, PR

    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_2_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
    2
    1.37
    sembles
    1.03
    wych
    1.03
    heus
    1.01
    િક
    0.98
    st
    0.97
    ed
    0.95
    liability
    0.95
    ne
    0.94
    9
    0.94
    POSITIVE LOGITS
    "
    1.40
    ู
    1.38
    س
    1.35
    ור
    1.34
    هم
    1.33
    是
    1.20
    一些
    1.19
    ко
    1.16
    רו
    1.14
    "。
    1.13
    Activations Density 0.001%

    No Known Activations