© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11579
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, with a slight tendency towards negative things

    oai_token-act-pair · gemini-2.0-flash

    narrative

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    They
    -0.86
     They
    -0.83
     they
    -0.77
     that
    -0.76
    they
    -0.74
     he
    -0.73
    He
    -0.72
     THEY
    -0.65
    We
    -0.64
     He
    -0.64
    POSITIVE LOGITS
    GEBURTSDATUM
    0.89
     дописавши
    0.88
     GenerationType
    0.86
     kaynağından
    0.72
    PreferredItem
    0.67
     estekak
    0.67
    ReusableCell
    0.65
     disambiguazione
    0.64
    IUrlHelper
    0.63
    
    0.63
    Activations Density 8.645%

    No Known Activations