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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12898
    Prev
    Next
    INDEX
    Explanations

    angle brackets, "String" and "Map", suggesting search for code that declares an object as a map of strings

    oai_token-act-pair · gemini-2.0-flash

    string

    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
    oredCriteria
    -0.58
     تضيفلها
    -0.50
    Doh
    -0.48
     calendriers
    -0.46
    mbols
    -0.46
     tenerife
    -0.46
     présentation
    -0.45
     stratég
    -0.45
    gura
    -0.45
    hnung
    -0.44
    POSITIVE LOGITS
    writerow
    0.69
    principalColumn
    0.68
    Autoritní
    0.68
    :✨
    0.66
     kasarigan
    0.63
    قایناق‌لار
    0.62
    writeFieldEnd
    0.62
    GTCX
    0.58
    angliski
    0.57
    GEBURTS
    0.56
    Activations Density 0.206%

    No Known Activations