© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2998
    Prev
    Next
    INDEX
    Explanations

    words that end in prefixes or suffixes that are not very common, or words that are proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    closing punctuation

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
    LY
    -0.69
    ism
    -0.68
    2
    -0.68
    5
    -0.65
    ,
    -0.62
     I
    -0.61
    /
    -0.59
    ah
    -0.59
    7
    -0.59
    -
    -0.56
    POSITIVE LOGITS
    '],
    1.02
    ("]");
    0.98
    }';
    0.97
    ConstraintMaker
    0.96
    )';
    0.94
    ]';
    0.94
    ftagPool
    0.94
    "],
    0.92
    :✨
    0.92
    ']],
    0.90
    Activations Density 11.055%

    No Known Activations