© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3194
    Prev
    Next
    INDEX
    Explanations

    phrases that describe different things having something in common or related

    oai_token-act-pair · gemini-2.0-flash

    programming-related terminology or phrases

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

    something

    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
     having
    -1.37
    having
    -1.28
    Having
    -1.17
     had
    -1.16
     Having
    -1.16
    have
    -1.13
     Have
    -1.07
    Have
    -1.07
     have
    -1.06
     HAVING
    -1.05
    POSITIVE LOGITS
     AssemblyCulture
    0.78
    ⓧ
    0.77
    DeleteBehavior
    0.75
    Démographie
    0.70
    Demografía
    0.62
    aarrggbb
    0.59
    SequentialGroup
    0.59
    RegressionTest
    0.58
    woor
    0.58
    Nazionale
    0.57
    Activations Density 0.694%

    No Known Activations