© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4627
    Prev
    Next
    INDEX
    Explanations

    phrases using the word "known"

    oai_token-act-pair · gemini-2.0-flash

    known

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Roskov
    -0.79
    Kanpo
    -0.67
     متعلقه
    -0.64
    Portail
    -0.63
    jsxFileName
    -0.60
    ItemBackground
    -0.59
    principalTable
    -0.57
    évaluateur
    -0.56
     MainAxisSize
    -0.56
    :✨
    -0.54
    POSITIVE LOGITS
     everywhere
    0.51
    Vidite
    0.50
     shadow
    0.50
     dés
    0.49
    fertig
    0.49
    quares
    0.48
    butt
    0.48
    Kilder
    0.47
    fromnode
    0.47
    NgModule
    0.46
    Activations Density 1.137%

    No Known Activations