© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 326
    Prev
    Next
    INDEX
    Explanations

    content related to linear algebra equations and operators

    oai_token-act-pair · gemini-2.0-flash

    Operator, operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ExecuteAsync
    -0.74
     برانيه
    -0.73
    +#+#
    -0.68
    posedge
    -0.68
     AttributeSet
    -0.67
    LookAnd
    -0.67
     fieldNum
    -0.66
     MainAxisSize
    -0.65
    OwnProperty
    -0.64
     defaultstate
    -0.64
    POSITIVE LOGITS
    XmlAccessType
    0.48
     isComment
    0.48
     spermat
    0.42
    ERRY
    0.40
    簧
    0.39
    Leod
    0.39
    pathy
    0.39
    ÚS
    0.39
     translateY
    0.39
    ето
    0.38
    Activations Density 3.509%

    No Known Activations