© 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. 204483
    Prev
    Next
    INDEX
    Explanations

    pretending

    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
    s
    1.36
    i
    1.25
    ع
    1.24
    im
    1.19
    6
    1.16
    it
    1.15
    ിയ
    1.12
    f
    1.12
    a
    1.09
    8
    1.08
    POSITIVE LOGITS
    শোধ
    0.88
    ческом
    0.88
    <unused209>
    0.88
     ήταν
    0.87
    唕
    0.86
    䢀
    0.86
    }]$.
    0.85
     редакти
    0.84
     опубли
    0.83
     industrious
    0.83
    Activations Density 0.001%

    No Known Activations