© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3241
    Prev
    Next
    INDEX
    Explanations

    prepositions, conjunctions, and other words that establish relationships between different parts of a sentence.

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.84
     disambiguazione
    -0.60
    SharedDtor
    -0.52
    ")}
    -0.51
     Walkover
    -0.49
    setVerticalGroup
    -0.48
    modb
    -0.48
    })).
    -0.47
    mapreduce
    -0.45
     <=",
    -0.45
    POSITIVE LOGITS
     poffe
    0.62
     leaſt
    0.60
     ſeveral
    0.60
     slightest
    0.59
    felves
    0.57
    TextBoxColumn
    0.57
    glTexCoord
    0.54
     pleaſure
    0.54
    ?,?,
    0.53
     ſtate
    0.53
    Activations Density 7.824%

    No Known Activations