© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15053
    Prev
    Next
    INDEX
    Explanations

    prepositions that join phrases indicating action and relationships between individuals, sometimes in sexually explicit scenarios.

    oai_token-act-pair · gemini-2.0-flash

    his

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     he
    -0.71
    He
    -0.61
     он
    -0.57
    he
    -0.52
    Ivoire
    -0.50
     hee
    -0.48
     той
    -0.44
     ơi
    -0.41
     Савез
    -0.41
    itten
    -0.40
    POSITIVE LOGITS
     his
    2.88
    his
    2.31
    His
    2.13
     His
    1.98
     HIS
    1.74
     hänen
    1.64
     seine
    1.63
    彼の
    1.61
     seiner
    1.60
     그의
    1.59
    Activations Density 10.736%

    No Known Activations