© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6536
    Prev
    Next
    INDEX
    Explanations

    android code related to image resources and layout

    oai_token-act-pair · gemini-2.0-flash

    code elements or attributes

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

    ="@

    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
    StructEnd
    -0.58
    ]")]
    -0.54
    󠁢
    -0.51
    versiti
    -0.49
    GIH
    -0.49
     հղումներ
    -0.48
    XmlEnum
    -0.48
     nakalista
    -0.48
    /**
    -0.48
     كومونز
    -0.48
    POSITIVE LOGITS
     الاطلاع
    0.63
    كذا
    0.60
     الدولى
    0.55
    mstyle
    0.52
    crollView
    0.51
    ưỡi
    0.51
     spoiling
    0.50
    maßen
    0.49
    Salta
    0.49
     pod
    0.49
    Activations Density 0.648%

    No Known Activations