© 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. 11949
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations that start with 'Th'

    oai_token-act-pair · gemini-2.0-flash

    th

    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
     >=",
    -0.68
    AsUp
    -0.68
    __':
    -0.63
    __":
    -0.62
     kasarigan
    -0.61
    новниш
    -0.61
     propOrder
    -0.60
     AssemblyProduct
    -0.58
     initComponents
    -0.56
     Administrativna
    -0.51
    POSITIVE LOGITS
    rians
    0.64
    Ự
    0.59
    riculture
    0.58
    ISupport
    0.57
    uesday
    0.57
    wollen
    0.57
    rification
    0.56
    rufe
    0.56
    wende
    0.56
    resher
    0.56
    Activations Density 9.832%

    No Known Activations