© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12872
    Prev
    Next
    INDEX
    Explanations

    greetings and forum-related language

    oai_token-act-pair · gemini-2.0-flash

    mentions of "Hi" or greetings

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

    greetings/introductions

    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
     {}),
    -0.52
     Geraadpleegd
    -0.47
    ________________
    -0.47
    ClientRect
    -0.46
    hst
    -0.45
     GTO
    -0.45
    Azur
    -0.45
    Cyfeiriadau
    -0.44
    jspb
    -0.43
     decentralized
    -0.43
    POSITIVE LOGITS
     its
    0.93
     Its
    0.84
     first
    0.79
    Its
    0.76
     JpaRepository
    0.65
    ValueGeneration
    0.64
    principalColumn
    0.60
    first
    0.59
    tagHelperRunner
    0.58
    它的
    0.58
    Activations Density 2.269%

    No Known Activations