© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86038
    Prev
    Next
    INDEX
    Explanations

    merlin group, melbourne cricket, city, melomel, griffin, wool, duplicates, logic, combat

    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_3_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
    -
    0.96
    I
    0.84
    K
    0.79
    S
    0.75
    ]
    0.73
    =
    0.72
    {
    0.71
    е
    0.71
    g
    0.67
    )
    0.67
    POSITIVE LOGITS
    ي
    0.68
    ط
    0.63
    يو
    0.57
     Ма
    0.57
     Nem
    0.57
     Архи
    0.56
     Париж
    0.56
     Про
    0.55
     Моск
    0.55
     Пор
    0.55
    Activations Density 0.015%

    No Known Activations