© 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. 25596
    Prev
    Next
    INDEX
    Explanations

    social workers

    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
    ى
    0.82
     становништво
    0.64
    ్య
    0.64
     р
    0.62
     неболь
    0.60
     श्रमिक
    0.59
    [\
    0.59
     idiosyncratic
    0.59
     восстановления
    0.58
     فى
    0.58
    POSITIVE LOGITS
    of
    0.85
    i
    0.76
    about
    0.75
    ও
    0.73
    )
    0.72
    }
    0.71
     aziende
    0.66
    also
    0.64
    수상
    0.64
    un
    0.63
    Activations Density 0.001%

    No Known Activations