© 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. 4705
    Prev
    Next
    INDEX
    Explanations

    phrases associated with delaying or preventing something from happening.

    oai_token-act-pair · gemini-2.0-flash

    forms of the word "put" and its variations

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

    off

    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
    GIVEREF
    -0.65
    исленность
    -0.55
     chi̍t
    -0.52
    IonicModule
    -0.51
    دانشنامهٔ
    -0.51
    reciation
    -0.50
    QMetaType
    -0.50
    ientôt
    -0.50
    TagHelpers
    -0.49
    Lähteet
    -0.49
    POSITIVE LOGITS
     off
    1.38
     Off
    1.13
    Off
    1.11
    off
    1.11
     OFF
    0.96
    OFF
    0.91
    offs
    0.87
     offs
    0.83
     Putting
    0.80
    put
    0.69
    Activations Density 1.782%

    No Known Activations