© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175341
    Prev
    Next
    INDEX
    Explanations

    legal termination of employment or housing

    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_20_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
     suscept
    0.47
    ↵
    0.47
     Surveillance
    0.43
    _-
    0.42
     Service
    0.41
     persons
    0.41
     susceptible
    0.41
     संभावित
    0.39
    ),
    0.39
    ვე
    0.39
    POSITIVE LOGITS
     шокола
    0.49
     дает
    0.46
     семина
    0.46
     함수의
    0.46
    পুত্র
    0.46
    🎋
    0.45
     ikan
    0.44
    ఠ
    0.43
     освобо
    0.43
     бүт
    0.43
    Activations Density 0.000%

    No Known Activations