© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11624
    Prev
    Next
    INDEX
    Explanations

    noun phrases acting as subjects within legal or computing contexts, accompanied by related verbs or adjectives

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    styleType
    -0.81
    Geplaatst
    -0.78
    OGND
    -0.70
     виправивши
    -0.66
     صوتيه
    -0.64
    stateProvider
    -0.61
     igång
    -0.60
    findpost
    -0.59
    addContainerGap
    -0.58
    routeProvider
    -0.58
    POSITIVE LOGITS
    临
    0.63
     slowly
    0.53
    ">//
    0.53
    臨
    0.53
     pulumi
    0.50
    cl
    0.49
     gradually
    0.48
     bob
    0.48
     ejec
    0.47
    awat
    0.46
    Activations Density 0.426%

    No Known Activations