© 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. 14220
    Prev
    Next
    INDEX
    Explanations

    phrases including "look forward"

    oai_token-act-pair · gemini-2.0-flash

    planning for the future

    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
     Forward
    -1.77
     forward
    -1.77
    Forward
    -1.69
     FORWARD
    -1.57
    forward
    -1.56
    FORWARD
    -1.27
     forwarding
    -1.13
     forwards
    -1.09
     forwarded
    -0.82
     fwd
    -0.79
    POSITIVE LOGITS
     ahead
    1.60
    ahead
    1.38
     Ahead
    1.32
     AHEAD
    1.25
    Ahead
    1.22
     beforehand
    0.56
    xtures
    0.54
     Slade
    0.54
     lined
    0.50
     Payments
    0.49
    Activations Density 3.769%

    No Known Activations