© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6269
    Prev
    Next
    INDEX
    Explanations

    words related to religious ministry and calling

    oai_token-act-pair · gemini-2.0-flash

    Academic/legal text

    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
    TagMode
    -0.63
    UnitTesting
    -0.60
     оригіналу
    -0.59
    RenderAtEndOf
    -0.59
    AndEndTag
    -0.59
    TagHelper
    -0.57
     cref
    -0.57
     Baillargeon
    -0.56
    Personendaten
    -0.56
    extAlignment
    -0.56
    POSITIVE LOGITS
    Viitteet
    0.54
     surla
    0.48
     jsPsych
    0.47
    σχ
    0.47
    genous
    0.46
     >=",
    0.45
    scher
    0.43
    fountain
    0.43
    oneof
    0.43
    例句
    0.42
    Activations Density 6.068%

    No Known Activations