© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1475
    Prev
    Next
    INDEX
    Explanations

    language describing the features of a retro gaming product

    oai_token-act-pair · gemini-2.0-flash

    Computer input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IsContent
    -0.57
    Tikang
    -0.56
    Aholisi
    -0.55
    กรณ์
    -0.54
    MigrationBuilder
    -0.54
    LookAnd
    -0.50
    jspb
    -0.49
     santé
    -0.48
    EndGlobalSection
    -0.47
    بیل
    -0.45
    POSITIVE LOGITS
     XCTest
    0.64
    stdc
    0.62
    mbals
    0.59
    createServer
    0.56
    ímite
    0.54
    média
    0.54
    PerformLayout
    0.53
    точ
    0.53
    ριν
    0.52
    setupUi
    0.52
    Activations Density 14.773%

    No Known Activations