© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12688
    Prev
    Next
    INDEX
    Explanations

    the word "and," sometimes near "by" or "or" and words that are sometimes associated with mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ArrowToggle
    -0.84
    MergeFrom
    -0.66
    featureID
    -0.65
    ItemBackground
    -0.60
    ganj
    -0.59
    WireFormatLite
    -0.59
    onAttach
    -0.59
    EDEFAULT
    -0.58
    RegistryLite
    -0.58
    IComponent
    -0.56
    POSITIVE LOGITS
     gynhyrchwyd
    0.57
    الحياه
    0.56
    LookAnd
    0.54
     StatelessWidget
    0.50
    OGND
    0.44
    هنگ
    0.42
    TagMode
    0.41
     StatefulWidget
    0.41
     noDo
    0.40
     CURLOPT
    0.40
    Activations Density 0.272%

    No Known Activations