© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8774
    Prev
    Next
    INDEX
    Explanations

    HTML list elements

    oai_token-act-pair · gemini-2.0-flash

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Giz
    -0.66
     Mez
    -0.60
     ZS
    -0.58
     FZ
    -0.57
    ynchronously
    -0.55
     GeoNames
    -0.55
    Personensuche
    -0.55
     Amadeus
    -0.54
     bows
    -0.54
     nests
    -0.54
    POSITIVE LOGITS
    XmlAccessType
    0.60
    sumi
    0.57
    ulli
    0.56
    templateUrl
    0.55
    lass
    0.53
    ----</
    0.51
    lccccc
    0.51
    includegraphics
    0.51
    SequentialGroup
    0.50
    stateMutability
    0.49
    Activations Density 7.288%

    No Known Activations