© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6961
    Prev
    Next
    INDEX
    Explanations

    phrases that people use when giving political opinions.

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    Random lengthy texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    webElementXpaths
    -0.63
    exitRule
    -0.58
    matchCondition
    -0.54
     فريبيس
    -0.54
    verwijspagina
    -0.52
    stateProvider
    -0.48
     hjer
    -0.47
    bewerken
    -0.46
    İZ
    -0.45
    ขึ้น
    -0.44
    POSITIVE LOGITS
     оригіналу
    0.62
     actionMode
    0.57
    Assert
    0.57
     finds
    0.55
     Assert
    0.54
     草
    0.54
    Naissance
    0.53
     Tors
    0.53
    estones
    0.52
     виправивши
    0.52
    Activations Density 2.373%

    No Known Activations