© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    named entities, specifically people and places, along with dates

    oai_token-act-pair · gemini-2.0-flash

    non-English words or code syntax

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

    Utah related

    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
    XmlType
    -0.62
     jsPsych
    -0.61
    Batis
    -0.48
     tymp
    -0.46
    complexType
    -0.45
     dimer
    -0.44
    Const
    -0.44
     Hopf
    -0.42
    VersionUID
    -0.42
     dna
    -0.42
    POSITIVE LOGITS
     חיצוניים
    0.69
    ClientSize
    0.68
     الحره
    0.67
     دریافت‌شده
    0.65
     насељу
    0.65
    Hozzáférés
    0.65
    abestanden
    0.59
    BuildContext
    0.57
    ])));
    0.57
    reactivex
    0.56
    Activations Density 0.171%

    No Known Activations