© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5300
    Prev
    Next
    INDEX
    Explanations

    a variety of intensifiers and comparatives, plus associated words

    oai_token-act-pair · gemini-2.0-flash

    life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Италијани
    -0.73
    HostException
    -0.60
    rophes
    -0.56
    NameInMap
    -0.56
    buttonBar
    -0.54
    PRNewswire
    -0.53
    └──
    -0.51
    Hozzáférés
    -0.50
     Pingback
    -0.49
     beginnetje
    -0.49
    POSITIVE LOGITS
     life
    2.56
    life
    2.17
     Life
    2.13
    Life
    2.05
     LIFE
    1.88
    LIFE
    1.78
     lifes
    1.38
     vida
    1.37
     Leben
    1.36
    lifes
    1.34
    Activations Density 2.324%

    No Known Activations