© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30690
    Prev
    Next
    INDEX
    Explanations

    **bold**

    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_31_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
    ธิบาย
    0.42
    웨어
    0.38
    (\|
    0.36
     wavefunction
    0.35
     And
    0.34
     xvi
    0.34
    zesz
    0.33
    }}(\
    0.33
    istry
    0.32
    重心
    0.32
    POSITIVE LOGITS
    有些
    0.40
     bold
    0.39
    ຕ
    0.39
    指
    0.38
    Bold
    0.38
     boldness
    0.37
     organisme
    0.36
     অপ্র
    0.36
     spoil
    0.36
    同樣
    0.35
    Activations Density 0.009%

    No Known Activations