© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1284
    Prev
    Next
    INDEX
    Explanations

    capitalized words and phrases, especially titles of creative works, and words relating to the general topic of sales

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    ervlak
    -0.50
     jspb
    -0.50
     enthusiasm
    -0.48
     familiarity
    -0.48
     فريبيس
    -0.48
    NullCheck
    -0.47
    anskje
    -0.47
     ambition
    -0.47
     motivation
    -0.45
     vex
    -0.45
    POSITIVE LOGITS
     Савезне
    0.67
    Autoritní
    0.61
    gemaakt
    0.60
     producteurs
    0.59
     reç
    0.58
    Diweddarwch
    0.57
     élevées
    0.57
    literals
    0.57
     applicazione
    0.56
     Campionato
    0.56
    Activations Density 3.638%

    No Known Activations