© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12489
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, especially those mentioning "years" or looking toward "what's in store".

    oai_token-act-pair · gemini-2.0-flash

    words related to future predictions

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

    ahead

    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
    SizeF
    -0.58
     doPost
    -0.54
    DrawerToggle
    -0.54
    ///</
    -0.53
     nargin
    -0.52
    rame
    -0.50
    Zunanje
    -0.49
     Pij
    -0.49
    BorderSize
    -0.48
    AddHtmlAttribute
    -0.48
    POSITIVE LOGITS
     ahead
    2.47
     Ahead
    2.17
    ahead
    2.06
     AHEAD
    2.06
    Ahead
    1.91
    переди
    1.15
     lies
    1.11
     lie
    1.10
     delante
    0.91
     lying
    0.88
    Activations Density 2.121%

    No Known Activations