© 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. 137671
    Prev
    Next
    INDEX
    Explanations

    portion

    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
    朋友們
    0.59
     fireball
    0.55
     songwriters
    0.55
    ্যাম্প
    0.54
     പിന്തു
    0.52
    燹
    0.50
     दोस्तों
    0.49
    वले
    0.49
    ensioni
    0.49
    oter
    0.48
    POSITIVE LOGITS
    .”.
    0.58
     чём
    0.55
    Чем
    0.52
     conduction
    0.52
    .".
    0.51
    .");
    0.51
     чем
    0.51
    ?,
    0.50
    Balance
    0.50
    4
    0.50
    Activations Density 0.000%

    No Known Activations