© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9993
    Prev
    Next
    INDEX
    Explanations

    words describing parts of a house

    oai_token-act-pair · gemini-2.0-flash

    doors and windows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     purpoſe
    -0.77
    SourceChecksum
    -0.75
     houſe
    -0.75
     ſche
    -0.71
     ſch
    -0.69
     Houſe
    -0.68
     ſtate
    -0.67
    ThroughAttribute
    -0.65
    NameInMap
    -0.64
    GraphicsUnit
    -0.63
    POSITIVE LOGITS
    si
    0.52
     virtuel
    0.51
    SI
    0.50
    IndentedString
    0.49
    simum
    0.49
    jsxFileName
    0.47
     transfieras
    0.46
    internalType
    0.44
    roffen
    0.44
     werking
    0.44
    Activations Density 1.435%

    No Known Activations