© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9976
    Prev
    Next
    INDEX
    Explanations

    words used as connecting words in sentences, especially to signal a continuation of thought in the first person

    oai_token-act-pair · gemini-2.0-flash

    blog entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    __":
    -0.66
    __':
    -0.61
    nhung
    -0.60
    SharedDtor
    -0.58
    bewerken
    -0.57
    NameInMap
    -0.55
    íslu
    -0.54
    __":
    -0.54
    .")
    -0.53
    %}
    -0.52
    POSITIVE LOGITS
     Return
    0.56
    RectangleBorder
    0.52
     return
    0.50
     vettoriale
    0.50
     astore
    0.50
     boite
    0.49
    attente
    0.49
     mắt
    0.49
     Âge
    0.49
    BufferException
    0.47
    Activations Density 28.157%

    No Known Activations