© 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. 4875
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a shift in understanding or perspective

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "clear"

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

    clear

    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
    __))
    -0.51
     виправивши
    -0.47
    ThroughAttribute
    -0.47
     beginnetje
    -0.46
    <!--[
    -0.45
    LastModified
    -0.43
    StreetMap
    -0.43
    ,',
    -0.41
     referenties
    -0.40
     advers
    -0.40
    POSITIVE LOGITS
     clear
    1.69
    clear
    1.45
     Clear
    1.35
    Clear
    1.34
     CLEAR
    1.32
    CLEAR
    1.25
     plain
    1.23
     clears
    1.18
     clearest
    1.14
     clearer
    1.10
    Activations Density 1.949%

    No Known Activations