© 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. 3340
    Prev
    Next
    INDEX
    Explanations

    words related to clothing, age, time, dates, and potentially negative personality traits or work environment issues

    oai_token-act-pair · gemini-2.0-flash

    say "shirt"

    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
    ".
    -0.53
    utilisons
    -0.51
    %";
    -0.47
     PSV
    -0.47
    ThemeOverlay
    -0.46
    Personendaten
    -0.46
     Stok
    -0.46
     bParam
    -0.46
     cts
    -0.45
     canst
    -0.44
    POSITIVE LOGITS
    daddy
    0.53
    balleur
    0.50
    billy
    0.50
    fucking
    0.49
    Rihanna
    0.49
    Daddy
    0.48
    laughing
    0.47
    bitch
    0.45
     للمعارف
    0.45
    daughter
    0.45
    Activations Density 14.277%

    No Known Activations