© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7106
    Prev
    Next
    INDEX
    Explanations

    "legal consequences financial and serious issues"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    rawData
    2.32
     processions
    2.20
     encarg
    2.15
     daž
    2.15
    ravi
    2.03
    ন্ত্রী
    2.00
    éu
    2.00
    জ
    1.99
    canonical
    1.99
    એ
    1.98
    POSITIVE LOGITS
     bylaws
    2.38
    र
    2.27
    êu
    2.22
    आत
    2.18
     awaken
    2.10
     instr
    2.10
    ਤਾ
    2.04
    化的
    2.01
    al
    2.00
    ु
    2.00
    Activations Density 0.028%

    No Known Activations