© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20168
    Prev
    Next
    INDEX
    Explanations

    real

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    塚
    0.36
     पार्षद
    0.33
    jana
    0.33
    etzte
    0.33
    iamiento
    0.33
    িন্ত
    0.32
    ඳු
    0.32
    렁
    0.32
    ൊ
    0.31
    िकेट
    0.31
    POSITIVE LOGITS
     real
    3.97
    real
    3.64
    Real
    3.48
     реа
    3.47
     Real
    3.34
     रियल
    3.02
    实
    2.89
    REAL
    2.81
     REAL
    2.73
    実
    2.66
    Activations Density 0.139%

    No Known Activations