© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2893
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tend" and phrases that signal someone's perspective or a lack of something

    oai_token-act-pair · gemini-2.0-flash

    tend/tends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyProduct
    -0.84
     imprimée
    -0.68
    =$?
    -0.64
    webElementXpaths
    -0.63
     quelcon
    -0.63
    Slut
    -0.60
     plastiques
    -0.59
     normaux
    -0.58
    UserScript
    -0.58
     extérieures
    -0.57
    POSITIVE LOGITS
    to
    0.64
     yield
    0.61
     unto
    0.59
     evoke
    0.56
    To
    0.55
     threaten
    0.54
     aggravate
    0.54
     underlie
    0.53
     encompass
    0.53
     contradict
    0.53
    Activations Density 9.044%

    No Known Activations