© 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. 12125
    Prev
    Next
    INDEX
    Explanations

    the phrase "going ahead" or "proceed"

    oai_token-act-pair · gemini-2.0-flash

    phrases related to moving forward or proceeding

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

    going/moving

    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
     समीक्षक
    -0.69
    脚注の使い方
    -0.63
    GOTREF
    -0.63
    stdafx
    -0.61
    AddTagHelper
    -0.59
     himo
    -0.59
     EconPapers
    -0.56
    InSection
    -0.55
     kaarangay
    -0.55
    awtextra
    -0.55
    POSITIVE LOGITS
     ahead
    1.48
    ahead
    1.25
     Ahead
    1.15
     AHEAD
    1.13
    Ahead
    1.05
     forward
    0.57
    Forward
    0.51
    enoord
    0.49
    ParallelGroup
    0.49
    forward
    0.49
    Activations Density 0.914%

    No Known Activations