© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12062
    Prev
    Next
    INDEX
    Explanations

    the word "and", but also sometimes other conjunctions and words related to amount/size/degree

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    DockStyle
    -0.69
    ]`
    -0.60
    ViewImports
    -0.58
    ÁND
    -0.56
     And
    -0.56
    })`
    -0.55
    >`;
    -0.54
    
    -0.54
    ."));
    -0.54
     ]];
    -0.54
    POSITIVE LOGITS
    ,
    0.60
     pirata
    0.56
    assium
    0.56
     لينك
    0.56
     muslin
    0.55
     typelib
    0.53
    cyklopedia
    0.53
    tichetta
    0.53
    ñores
    0.52
     newBuilder
    0.52
    Activations Density 2.155%

    No Known Activations