© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3539
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical equations and code, and Android Intents

    oai_token-act-pair · gemini-2.0-flash

    variations of i

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    principalTable
    -0.45
    fsch
    -0.42
    ATEUR
    -0.40
    KURZBESCHREIBUNG
    -0.39
    ORY
    -0.39
    æa
    -0.39
    unknownFields
    -0.39
     propOrder
    -0.38
    ETY
    -0.37
    rawDesc
    -0.37
    POSITIVE LOGITS
     i
    1.45
    i
    1.35
    ｉ
    1.09
    iI
    1.05
    ii
    1.05
     ii
    1.02
    Ii
    1.00
    𝑖
    0.99
    iS
    0.93
     ih
    0.93
    Activations Density 18.238%

    No Known Activations