© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5858
    Prev
    Next
    INDEX
    Explanations

    words related to dog behavior, especially on a leash

    oai_token-act-pair · gemini-2.0-flash

    dogs

    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
    Климат
    -0.74
    
    -0.72
     Roskov
    -0.71
     Himo
    -0.70
    MLLoader
    -0.69
    UserScript
    -0.67
    ViewChild
    -0.65
    WSGI
    -0.65
     Wikimedijinoj
    -0.64
    Бахар
    -0.64
    POSITIVE LOGITS
    eno
    0.47
     CreateTagHelper
    0.46
     invokingState
    0.46
    hae
    0.43
     genti
    0.42
     Wolf
    0.42
     working
    0.42
    рабо
    0.41
    oy
    0.41
     search
    0.40
    Activations Density 0.789%

    No Known Activations