© 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. 12927
    Prev
    Next
    INDEX
    Explanations

    sentences that attribute information to a source

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     للاسماء
    -0.89
     autorytatywna
    -0.84
    rungsseite
    -0.70
    <bos>
    -0.66
    Autoritní
    -0.65
    MigrationBuilder
    -0.65
    SourceChecksum
    -0.65
    parsedMessage
    -0.63
    ⓧ
    -0.61
    webElementXpaths
    -0.61
    POSITIVE LOGITS
     BitmapFactory
    0.66
    
    0.53
     BorderSide
    0.44
     Serbie
    0.44
    TryParse
    0.44
    icolon
    0.43
    的说道
    0.43
    IGOS
    0.42
    NumberFormat
    0.42
     defStyle
    0.41
    Activations Density 0.320%

    No Known Activations