© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    references to personal and possessive pronouns, family relations, and personal circumstances in detailed articles

    oai_token-act-pair · gemini-2.0-flash

    general language use

    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
     an
    -0.81
     is
    -0.65
     a
    -0.65
     has
    -0.64
     are
    -0.64
     have
    -0.57
     the
    -0.54
    ztés
    -0.51
     tenha
    -0.48
    ジュアル
    -0.47
    POSITIVE LOGITS
    .
    0.94
     for
    0.91
     AssemblyProduct
    0.85
     that
    0.84
     at
    0.80
    .');
    0.77
    .");
    0.76
     समीक्षक
    0.73
     CreateTagHelper
    0.71
    .).
    0.70
    Activations Density 22.708%

    No Known Activations