© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11283
    Prev
    Next
    INDEX
    Explanations

    strings or characters used in programming code like parentheses, quotes, or standard output statements in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    Parentheses and quotation marks

    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
    ordo
    -0.47
     prefier
    -0.46
    лександ
    -0.44
     externo
    -0.41
    vrons
    -0.41
     fortæller
    -0.40
     Participating
    -0.40
    λία
    -0.40
    tagext
    -0.40
     prefers
    -0.39
    POSITIVE LOGITS
    PerformLayout
    0.78
    UnsafeEnabled
    0.74
     oprot
    0.73
     BoxFit
    0.73
     виправивши
    0.69
    FormTagHelper
    0.64
    uxxxx
    0.64
     tartalomajánló
    0.63
    पया
    0.63
    balleur
    0.61
    Activations Density 1.166%

    No Known Activations