© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11020
    Prev
    Next
    INDEX
    Explanations

    language contrasting two things, especially with 'but' and 'yet'

    oai_token-act-pair · gemini-2.0-flash

    conjunctions and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Zing
    -0.52
    +][
    -0.51
    xelles
    -0.50
    }")]
    -0.50
    Demografie
    -0.50
    本当は
    -0.49
    そりゃ
    -0.49
    êng
    -0.49
    okie
    -0.49
    阅读原文
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.69
    findpost
    0.66
    WebVitals
    0.65
    IntoConstraints
    0.65
    providedIn
    0.62
    BASEPATH
    0.62
     gynhyrchwyd
    0.59
    NameInMap
    0.58
    StructEnd
    0.58
    UnitTesting
    0.54
    Activations Density 0.325%

    No Known Activations