© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14655
    Prev
    Next
    INDEX
    Explanations

    a particular style of writing used in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    Materials science and chemistry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WebElementEntity
    -0.75
    TargetException
    -0.70
    hyrchwyd
    -0.68
    ostok
    -0.64
    ArrowToggle
    -0.63
    IndentedString
    -0.63
    PreferredItem
    -0.62
     poffe
    -0.61
    EndGlobalSection
    -0.60
     ftate
    -0.59
    POSITIVE LOGITS
    
    0.46
    lielmo
    0.43
    ########.
    0.41
    <()>
    0.40
    bnf
    0.38
     candidato
    0.37
    bord
    0.37
    iture
    0.37
    高度
    0.36
    laug
    0.36
    Activations Density 1.747%

    No Known Activations