© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 15219
    Prev
    Next
    INDEX
    Explanations

    the phrase "in the first" or "for the"

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     first
    -1.25
    first
    -1.20
    First
    -1.16
     First
    -1.15
     FIRST
    -1.04
    FIRST
    -1.00
     initial
    -0.99
     firft
    -0.94
     first
    -0.92
     pertama
    -0.89
    POSITIVE LOGITS
     prime
    1.38
    prime
    1.26
     primary
    1.23
    Prime
    1.16
     Prime
    1.12
     PRIME
    1.11
    primary
    1.11
     primer
    1.10
     Primary
    1.08
    PRIME
    1.06
    Activations Density 0.792%

    No Known Activations