© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12067
    Prev
    Next
    INDEX
    Explanations

    table headings and formatting, regardless of the specific content

    oai_token-act-pair · gemini-2.0-flash

    Hyphens

    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
    __":
    -0.74
     autorytatywna
    -0.71
    IUrlHelper
    -0.70
    __':
    -0.65
    StructEnd
    -0.60
    aarrggbb
    -0.59
    StoryboardSegue
    -0.59
    AddTagHelper
    -0.59
    saraba
    -0.58
     MaterialApp
    -0.56
    POSITIVE LOGITS
    roma
    0.56
     متعلقه
    0.51
     sheet
    0.45
    ANTED
    0.44
     SHEET
    0.44
    örs
    0.44
    Digit
    0.43
     manuell
    0.43
     gái
    0.43
    AutoField
    0.42
    Activations Density 1.344%

    No Known Activations