© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7354
    Prev
    Next
    INDEX
    Explanations

    language expressing emotion and the human condition

    oai_token-act-pair · gemini-2.0-flash

    Feelings and emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    хьтан
    -0.56
    ోగ
    -0.53
    PHONY
    -0.51
     skills
    -0.49
     Qaraldi
    -0.48
    lanc
    -0.48
     Auer
    -0.48
    IFEST
    -0.48
     sợi
    -0.47
    Demografía
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.66
    KommentareTeilen
    0.63
    IntoConstraints
    0.59
    mybatisplus
    0.51
     dAtA
    0.50
    InstanceState
    0.49
     препратки
    0.48
    BarItem
    0.48
    Naissance
    0.47
     муніципалі
    0.46
    Activations Density 3.826%

    No Known Activations