© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8990
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and HTML attributes

    oai_token-act-pair · gemini-2.0-flash

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     ne
    -0.52
     
    -0.50
     "
    -0.50
    ;
    -0.49
     “
    -0.49
    ,
    -0.49
     (
    -0.48
     be
    -0.48
     p
    -0.48
    </b>
    -0.47
    POSITIVE LOGITS
     للاسماء
    1.08
     Савезне
    1.05
     nahilalakip
    0.96
    ThroughAttribute
    0.93
    oredCriteria
    0.91
    afficheront
    0.90
    ⓧ
    0.90
    LookAnd
    0.88
    rungsseite
    0.85
     ErrIntOverflow
    0.85
    Activations Density 1.686%

    No Known Activations