© 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. 14676
    Prev
    Next
    INDEX
    Explanations

    mentions of elephants either literal or figurative

    oai_token-act-pair · gemini-2.0-flash

    terms related to elephants

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

    trunk

    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
    antren
    -0.50
     LIABLE
    -0.48
     GMA
    -0.48
    IconModule
    -0.48
    ніципа
    -0.47
    arabe
    -0.47
     Спасибо
    -0.47
    lorette
    -0.47
     ITA
    -0.46
    NewUrlParser
    -0.46
    POSITIVE LOGITS
     trunk
    0.75
     tus
    0.68
     Trunk
    0.66
    Ele
    0.65
    webElementXpaths
    0.64
    trunk
    0.64
     trunks
    0.64
    HasAnnotation
    0.64
    //
    0.63
    achy
    0.62
    Activations Density 1.518%

    No Known Activations