© 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. 10343
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    oai_token-act-pair · gemini-2.0-flash

    Scientific notations

    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
     Roskov
    -1.14
    setVerticalGroup
    -1.12
    LookAnd
    -0.92
    +#+#
    -0.92
    AddTagHelper
    -0.91
    mybatisplus
    -0.88
    VersionUID
    -0.85
    AsUp
    -0.84
    Rhestr
    -0.84
     Мексичка
    -0.83
    POSITIVE LOGITS
    v
    0.45
     to
    0.43
    士
    0.42
    V
    0.42
    5
    0.42
    7
    0.42
    To
    0.39
    iVar
    0.39
    3
    0.39
     voler
    0.38
    Activations Density 3.981%

    No Known Activations