© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203997
    Prev
    Next
    INDEX
    Explanations

    specific details

    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_6_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
    ى
    1.31
     muốn
    1.14
     powied
    1.09
     过
    1.09
     değiştir
    1.07
     этом
    1.06
     articolo
    1.05
     añ
    1.04
     เมื่อ
    1.04
     edificios
    1.04
    POSITIVE LOGITS
    <
    1.20
    >
    1.19
    )
    0.99
    !=
    0.99
    (
    0.98
    :
    0.89
    ==
    0.87
    int
    0.86
    =
    0.86
    adress
    0.86
    Activations Density 0.000%

    No Known Activations