© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202965
    Prev
    Next
    INDEX
    Explanations

    ash tree type

    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_12_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
    )،
    0.62
     услу
    0.55
    '।
    0.55
     dólares
    0.54
    ных
    0.54
    🫰
    0.54
     hizmet
    0.54
     אשר
    0.54
     Матери
    0.53
    ]，
    0.53
    POSITIVE LOGITS
    t
    0.77
    at
    0.74
    st
    0.60
    im
    0.60
    us
    0.59
    atac
    0.58
    ab
    0.54
    vertical
    0.52
    test
    0.52
    medical
    0.52
    Activations Density 0.000%

    No Known Activations