© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9484
    Prev
    Next
    INDEX
    Explanations

    a mix of acronyms, names, and words relating to mathematics and computer science

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.79
    XtraEditors
    -0.49
    internal
    -0.46
     Internal
    -0.45
    >{@
    -0.44
    mach
    -0.44
    insics
    -0.43
    &#
    -0.43
    ’
    -0.42
     interne
    -0.42
    POSITIVE LOGITS
     Majefty
    0.92
     houſe
    0.88
     pleaſure
    0.87
     purpoſe
    0.87
     myſelf
    0.86
     Jefus
    0.82
     Efq
    0.81
     Reſ
    0.79
     ſever
    0.79
     themſelves
    0.79
    Activations Density 3.890%

    No Known Activations