© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3318
    Prev
    Next
    INDEX
    Explanations

    feelings and states of being

    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_5_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
    𝑏
    1.77
    𝑙
    1.73
    𝑧
    1.70
     receivables
    1.70
    𝑟
    1.70
    ਤਰ
    1.64
    至于
    1.64
    𝑒
    1.62
     bytecode
    1.58
    𝑠
    1.58
    POSITIVE LOGITS
     compelled
    1.60
    ület
    1.42
     nevoia
    1.37
    istic
    1.32
     Qxc
    1.32
    ies
    1.31
     vontade
    1.29
     sorry
    1.27
    వం
    1.26
    esinde
    1.26
    Activations Density 0.228%

    No Known Activations