© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to decision making and preferences

    oai_token-act-pair · gemini-2.0-flash

    Variations of the letter "w"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    UnknownFields
    -0.52
    seamnă
    -0.50
     angekommen
    -0.49
    AndEndTag
    -0.49
     ilustracja
    -0.49
    zuführen
    -0.49
     occupé
    -0.49
     barbati
    -0.48
     ordinaires
    -0.48
     étoient
    -0.47
    POSITIVE LOGITS
     w
    3.42
    w
    2.19
     W
    1.76
    W
    1.40
     wl
    1.25
    𝘄
    1.16
    ᴡ
    1.09
    𝐰
    1.05
     wn
    1.04
    𝑤
    1.04
    Activations Density 7.386%

    No Known Activations