© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10583
    Prev
    Next
    INDEX
    Explanations

    uses of the word "fit"

    oai_token-act-pair · gemini-2.0-flash

    fit or fall

    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
     submar
    -0.59
    Gön
    -0.52
    ">'.$
    -0.50
    restrial
    -0.49
     Carlisle
    -0.49
    íaco
    -0.48
    opel
    -0.48
     TextAppearance
    -0.48
     ſhould
    -0.47
     généraux
    -0.47
    POSITIVE LOGITS
    曖昧さ回避
    0.57
     MenuView
    0.53
    mità
    0.53
    Спољашње
    0.52
    новниш
    0.51
     nahilalakip
    0.50
    Бахар
    0.50
    comfortably
    0.50
    ariConfig
    0.49
    CloseOperation
    0.49
    Activations Density 1.736%

    No Known Activations