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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5709
    Prev
    Next
    INDEX
    Explanations

    language related to housing and energy, especially in the context of affordability and responsibility

    oai_token-act-pair · gemini-2.0-flash

    terms related to housing and rent

    np_token-act-pair-logits · gpt-4o-mini

    Rental properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RectangleBorder
    -0.59
     UIFont
    -0.54
    initComponents
    -0.53
    </tfoot>
    -0.53
     Mesozoic
    -0.52
     Hopf
    -0.52
     gracilis
    -0.51
     detain
    -0.50
    ModelState
    -0.48
     Mounted
    -0.48
    POSITIVE LOGITS
    MessageOf
    0.83
     rent
    0.64
    adaptiveStyles
    0.62
    CodedInputStream
    0.61
    tagext
    0.59
     الحره
    0.59
    下载附件
    0.59
    land
    0.59
     land
    0.57
     Rent
    0.57
    Activations Density 2.136%

    No Known Activations