© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10557
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and beliefs.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    assung
    -0.47
    lhes
    -0.47
    msgSender
    -0.47
    通販
    -0.46
     navideñas
    -0.46
     angesch
    -0.46
    zerű
    -0.45
    SceneManagement
    -0.45
    TagHelper
    -0.45
     térm
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.71
    AndEndTag
    0.65
     propOrder
    0.60
    Nazionale
    0.59
    ChildScrollView
    0.57
     Normdatei
    0.57
     ujednoznacz
    0.56
    rungsseite
    0.54
     Audiodateien
    0.53
     homo
    0.53
    Activations Density 1.985%

    No Known Activations