© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    c code defining constants and macros

    oai_token-act-pair · gemini-2.0-flash

    code and identifiers

    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
    same
    -0.47
    soft
    -0.47
     Use
    -0.46
    other
    -0.46
    SharedDtor
    -0.46
     And
    -0.45
    word
    -0.44
    theless
    -0.44
     Where
    -0.44
    some
    -0.43
    POSITIVE LOGITS
    IAR
    0.52
    ADORA
    0.51
    ILayout
    0.49
    ICZ
    0.49
    BDA
    0.48
    IAC
    0.47
    IDAE
    0.47
    AFE
    0.47
    LIA
    0.47
    AVEL
    0.47
    Activations Density 10.137%

    No Known Activations