© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9987
    Prev
    Next
    INDEX
    Explanations

    historical information related to war and political positions

    oai_token-act-pair · gemini-2.0-flash

    Military/Governmental operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <<<<<<<<<<<<<<
    -0.62
    SharedCtor
    -0.59
    asInstanceOf
    -0.55
    +#+#
    -0.54
     Lawton
    -0.53
    TableId
    -0.53
    DMETHOD
    -0.52
     TextEditing
    -0.52
    SerializedName
    -0.52
    migrationBuilder
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.72
    umel
    0.53
     disambiguazione
    0.51
     CreateTagHelper
    0.50
    @[+][
    0.49
    !*\
    0.47
     Sign
    0.46
    mau
    0.45
    Sign
    0.44
    ()?;
    0.43
    Activations Density 1.139%

    No Known Activations