© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    the prefix "fore"

    oai_token-act-pair · gemini-2.0-flash

    fore

    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
    InjectAttribute
    -1.02
     EconPapers
    -0.87
     AssemblyCulture
    -0.87
    principalColumn
    -0.86
    KommentareTeilen
    -0.86
    endphp
    -0.85
     snippetHide
    -0.85
    ItemBackground
    -0.85
    Diwedd
    -0.84
     oprot
    -0.82
    POSITIVE LOGITS
    Us
    0.37
    bės
    0.36
     Front
    0.33
     Schar
    0.33
    と思われる
    0.33
    Front
    0.31
     dig
    0.31
    rasing
    0.31
     star
    0.31
    word
    0.30
    Activations Density 0.789%

    No Known Activations