© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204433
    Prev
    Next
    INDEX
    Explanations

    filetype detection

    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_6_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
    <0x80>
    1.01
     to
    0.94
    ล
    0.84
    তত্ব
    0.80
    ە
    0.79
    ގެ
    0.77
    t
    0.77
     divulgação
    0.76
    নার্থ
    0.75
     Ли
    0.75
    POSITIVE LOGITS
    1.28
    of
    1.20
    ‌ای
    0.91
    ofthe
    0.90
    ו
    0.90
    }
    0.89
    )
    0.85
    :
    0.84
    -
    0.80
    im
    0.76
    Activations Density 0.003%

    No Known Activations