© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8303
    Prev
    Next
    INDEX
    Explanations

    a variety of non-alphanumeric characters such as hyphens, slashes, parentheses, and quotation marks

    oai_token-act-pair · gemini-2.0-flash

    hyphen/dash/quote

    np_max-act-logits · gemini-2.0-flash

    punctuation

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     x
    -0.59
     v
    -0.56
     Jansen
    -0.53
    发表于
    -0.52
     O
    -0.52
     V
    -0.50
     
    -0.50
     d
    -0.50
     var
    -0.50
    addCriterion
    -0.50
    POSITIVE LOGITS
     }}$}
    0.54
     ]
    0.48
     $_"
    0.47
    ſelves
    0.45
    )*/
    0.45
    .")
    0.44
     auffi
    0.44
    ".
    0.43
     //
    0.43
    ."],
    0.42
    Activations Density 11.094%

    No Known Activations