© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    things that appear to be numbers, formulas or tables of data

    oai_token-act-pair · gemini-2.0-flash

    numbers and fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    strix
    -0.47
    oredCriteria
    -0.46
    EDEFAULT
    -0.46
     iprot
    -0.45
     counsel
    -0.44
    lanatory
    -0.44
    Begriffsklä
    -0.43
    specialchars
    -0.43
     Ngb
    -0.42
     <>",
    -0.42
    POSITIVE LOGITS
     MainAxisSize
    0.67
     referenties
    0.65
    CloseOperation
    0.64
    rungsseite
    0.60
    tonode
    0.59
    __).
    0.58
    Portale
    0.56
    AnimationsModule
    0.56
     tartalomajánló
    0.56
    fromnode
    0.55
    Activations Density 12.324%

    No Known Activations