© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212280
    Prev
    Next
    INDEX
    Explanations

    ys ending 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_5_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
    is
    1.48
     on
    1.28
    ৬
    1.05
    in
    1.04
    em
    0.97
    ene
    0.93
    é
    0.93
    -\
    0.92
    />
    0.92
    ig
    0.88
    POSITIVE LOGITS
    ي
    1.13
     médias
    0.99
    ИТ
    0.99
    㞓
    0.97
    ঙ্গি
    0.94
    ICK
    0.92
    𝒕
    0.91
     eléctricas
    0.89
    нном
    0.89
    屇
    0.88
    Activations Density 0.002%

    No Known Activations