© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29033
    Prev
    Next
    INDEX
    Explanations

    deregulation and free market

    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_10_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
    s
    0.62
    ی
    0.54
    れ
    0.49
    ים
    0.47
    エ
    0.45
    েয়
    0.45
    sı
    0.45
    వ్ర
    0.43
     resuspended
    0.43
    اك
    0.43
    POSITIVE LOGITS
    ’
    0.55
    azard
    0.45
    ]
    0.45
    {
    0.43
    )’
    0.43
    us
    0.42
    ২০০
    0.42
    ozat
    0.42
    az
    0.42
    :}
    0.41
    Activations Density 0.029%

    No Known Activations