© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12678
    Prev
    Next
    INDEX
    Explanations

    name fragments which form names of cities, towns, or other locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    (");
    -0.60
    )}</
    -0.59
    beve
    -0.56
    ]<<"
    -0.52
    Сылтамалар
    -0.51
     ReactDOM
    -0.50
    ']>
    -0.49
    ']='
    -0.49
    ']?>
    -0.47
    ']=='
    -0.47
    POSITIVE LOGITS
     pleaſure
    0.65
     autorytatywna
    0.59
    /*
    0.56
    writeField
    0.54
    <bos>
    0.53
     udaler
    0.52
    VolleyError
    0.51
     Inſ
    0.51
     purpoſe
    0.50
    يكب
    0.49
    Activations Density 0.440%

    No Known Activations