© 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. 9273
    Prev
    Next
    INDEX
    Explanations

    interjections like "um", "ah", "uh", "er", or "well"

    oai_token-act-pair · gemini-2.0-flash

    non-English phrases

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

    Interjections

    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
    Хьажоргаш
    -0.64
    脚注の使い方
    -0.57
     '\\;'
    -0.54
     LUMP
    -0.52
    تقاوى
    -0.52
     flesta
    -0.50
    SizeF
    -0.50
     linkovi
    -0.48
    {{--
    -0.48
     outlook
    -0.48
    POSITIVE LOGITS
     استنادى
    0.61
    ManagedBean
    0.58
    EClass
    0.57
    __;
    0.55
    complexType
    0.55
    dataclass
    0.53
    ConstraintMaker
    0.51
    bbons
    0.50
    colorPrimary
    0.50
     متعلقه
    0.50
    Activations Density 1.098%

    No Known Activations