© 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. 553
    Prev
    Next
    INDEX
    Explanations

    text passages written in all capital letters

    oai_token-act-pair · gemini-2.0-flash

    general English text

    np_max-act-logits · gemini-2.0-flash

    say "space" Method used: 2 — pattern: tokens start with a space — say "space"

    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
    ]<<"
    -0.33
    CESO
    -0.33
    PHIA
    -0.31
    ]='\
    -0.28
    ÍO
    -0.28
    ÁF
    -0.28
    LOPT
    -0.27
    AJAS
    -0.27
    ]--;
    -0.27
    XICO
    -0.27
    POSITIVE LOGITS
     FOR
    0.77
     WITH
    0.73
     FROM
    0.73
     THE
    0.72
     THEY
    0.70
     WHEN
    0.70
     THERE
    0.70
     THROUGH
    0.69
     WHICH
    0.69
     ABOUT
    0.69
    Activations Density 76.859%

    No Known Activations