© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14678
    Prev
    Next
    INDEX
    Explanations

    words related to political and economic subjects

    oai_token-act-pair · gemini-2.0-flash

    suicide

    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
    astify
    -0.71
    tagHelperRunner
    -0.68
     consultato
    -0.66
    AsUp
    -0.66
     propOrder
    -0.65
    AndEndTag
    -0.63
    __*/
    -0.63
    CloseOperation
    -0.62
     disambiguazione
    -0.62
    DoubleQuotes
    -0.61
    POSITIVE LOGITS
     suicide
    0.55
    Chham
    0.51
    TagHelper
    0.50
    nieren
    0.46
    flage
    0.45
     Suicide
    0.45
     suicidal
    0.44
    baz
    0.43
     suicidio
    0.43
    自殺
    0.42
    Activations Density 4.263%

    No Known Activations