© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    words that express subjective opinion or sentiment, often with associated intensity

    oai_token-act-pair · gemini-2.0-flash

    very

    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
    rest
    -0.53
     prophecy
    -0.47
     balsam
    -0.46
     Variation
    -0.46
     scopo
    -0.45
     subsections
    -0.45
     Variations
    -0.45
    Rest
    -0.45
     reft
    -0.45
     variation
    -0.44
    POSITIVE LOGITS
    出版年
    0.85
    UnsafeEnabled
    0.82
     saites
    0.68
    uxxxx
    0.66
     säll
    0.65
    soort
    0.63
    PointerException
    0.62
     tää
    0.59
     AssemblyCulture
    0.58
     Roskov
    0.57
    Activations Density 1.609%

    No Known Activations