© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2884
    Prev
    Next
    INDEX
    Explanations

    the word "but" and other contrastive conjunctions and adverbs.

    oai_token-act-pair · gemini-2.0-flash

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    parsedMessage
    -0.54
    ướt
    -0.52
    MessageTagHelper
    -0.52
    SPATH
    -0.49
     estekak
    -0.48
    醐
    -0.48
    opsida
    -0.46
     japonaise
    -0.46
     excepción
    -0.45
     IUser
    -0.45
    POSITIVE LOGITS
    findpost
    0.68
     typelib
    0.62
    LookAnd
    0.60
    最快更新
    0.59
    XMLSchema
    0.58
    }?>
    0.56
    PagerAdapter
    0.55
    TabStop
    0.55
    SequentialGroup
    0.55
    eventbus
    0.52
    Activations Density 1.047%

    No Known Activations