© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211173
    Prev
    Next
    INDEX
    Explanations

    Social

    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_43_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
     পাকিস্তান
    0.39
    閤
    0.37
     পাকিস্তানি
    0.36
     Vent
    0.36
    𝖽
    0.36
     கி
    0.36
    लेंट
    0.36
    ួ
    0.36
    }`));
    0.35
    Logistic
    0.34
    POSITIVE LOGITS
     ESG
    0.91
     Impact
    0.84
     ESR
    0.79
     impact
    0.77
    ESG
    0.77
     CSR
    0.75
    Impact
    0.73
    impact
    0.71
     Social
    0.71
     social
    0.70
    Activations Density 0.003%

    No Known Activations