© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4982
    Prev
    Next
    INDEX
    Explanations

    colons

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash

    : Method used: 1 — because every max activating token is the colon character

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <b>
    -0.78
     
    -0.77
      
    -0.69
    ↵↵
    -0.67
    ...
    -0.66
    <strong>
    -0.65
    ..
    -0.64
    *
    -0.60
    “
    -0.60
    /
    -0.59
    POSITIVE LOGITS
     }}$}
    1.17
    ."]
    1.08
    ']")
    1.02
    .")]
    1.00
     Савезне
    1.00
    ."</
    1.00
    '")
    0.99
    ')));
    0.97
    ]";
    0.96
    ')))
    0.96
    Activations Density 0.996%

    No Known Activations