© 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. 9575
    Prev
    Next
    INDEX
    Explanations

    long chemical names in scientific documents

    oai_token-act-pair · gemini-2.0-flash

    nitro

    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
    Zeneca
    -0.49
    dega
    -0.49
    конец
    -0.44
     picada
    -0.43
    Slot
    -0.42
    tahui
    -0.42
     bianche
    -0.42
    arele
    -0.41
     !_
    -0.41
    bertura
    -0.40
    POSITIVE LOGITS
     unknownFields
    0.78
    ViewInit
    0.77
    __":
    0.70
    AddTagHelper
    0.70
    principalColumn
    0.69
     Pingback
    0.67
    Portale
    0.67
    __":
    0.66
    CopyWith
    0.64
    __':
    0.64
    Activations Density 1.833%

    No Known Activations