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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2347
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to size and combinations of things, possibly in a combat or science fiction context

    oai_token-act-pair · gemini-2.0-flash

    TV series descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DebuggerNonUser
    -0.65
     تضيفلها
    -0.64
    ContentAlignment
    -0.52
     harass
    -0.51
    PropertyGroup
    -0.49
    contentLoaded
    -0.49
    userModel
    -0.48
    ึกษา
    -0.47
    AddTagHelper
    -0.47
    OrBuilder
    -0.47
    POSITIVE LOGITS
     Huge
    1.25
     huge
    1.23
    Huge
    1.20
    huge
    1.20
     gigantic
    1.19
     HUGE
    1.16
     colossal
    1.05
     enormous
    1.04
     enorme
    1.02
     énorme
    1.01
    Activations Density 0.822%

    No Known Activations