© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 563
    Prev
    Next
    INDEX
    Explanations

    html code with the words "or" or "and" and "$"

    oai_token-act-pair · gemini-2.0-flash

    i or |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.20
    –
    -0.50
     чем
    -0.50
     th
    -0.50
     and
    -0.47
    th
    -0.45
     center
    -0.45
    ↵↵
    -0.44
    <u>
    -0.44
     still
    -0.43
    POSITIVE LOGITS
     InputDecoration
    1.05
     مشين
    0.93
     للاسماء
    0.83
     تانيه
    0.74
    rungsseite
    0.74
    ".
    0.72
     CreateTagHelper
    0.71
    ConstraintMaker
    0.70
    didSet
    0.69
    makeConstraints
    0.68
    Activations Density 1.256%

    No Known Activations