© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136311
    Prev
    Next
    INDEX
    Explanations

    charitable donations

    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_37_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
    gameOver
    0.44
    駆
    0.38
    keyPressed
    0.38
    対処
    0.38
    ्ला
    0.37
     Ró
    0.37
     खेतों
    0.36
    salted
    0.36
    }^{(
    0.36
     padx
    0.35
    POSITIVE LOGITS
     charity
    0.69
    慈善
    0.69
     charitable
    0.66
     Charitable
    0.66
     Charity
    0.65
     Charities
    0.61
     charities
    0.60
     donations
    0.57
     donated
    0.57
     donate
    0.55
    Activations Density 0.000%

    No Known Activations