© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9909
    Prev
    Next
    INDEX
    Explanations

    statements of possibility or suggestion

    oai_token-act-pair · gemini-2.0-flash

    words related to attempts or trying

    np_token-act-pair-logits · gpt-4o-mini

    try

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    LookAnd
    -0.69
    hyrchwyd
    -0.66
    RetentionPolicy
    -0.65
     تضيفلها
    -0.63
    :]:
    -0.60
     Drapeau
    -0.57
    بوابة
    -0.56
    javac
    -0.56
    UnusedPrivate
    -0.55
     للاسماء
    -0.55
    POSITIVE LOGITS
     try
    3.02
     tries
    2.67
    try
    2.67
     Try
    2.58
    Try
    2.56
     trying
    2.45
     attempt
    2.39
     tried
    2.38
     TRY
    2.36
     attempts
    2.20
    Activations Density 2.661%

    No Known Activations