© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    mostly commas and some numbers related to sports

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    LookAnd
    -0.85
     CreateTagHelper
    -0.83
     propOrder
    -0.80
     Paglinawan
    -0.77
    TypedDataSet
    -0.75
     NSCoder
    -0.74
     <=",
    -0.71
    AnchorStyles
    -0.69
    IContainer
    -0.69
     transfieras
    -0.68
    POSITIVE LOGITS
    jspx
    0.40
     type
    0.39
     možnost
    0.39
    distan
    0.36
    maßen
    0.36
     ImportError
    0.35
    type
    0.35
     stay
    0.35
    getCount
    0.34
     directe
    0.34
    Activations Density 0.005%

    No Known Activations