© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11594
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe an impact or effect of something

    oai_token-act-pair · gemini-2.0-flash

    impact/effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     MainAxisSize
    -0.70
     BorderRadius
    -0.69
     impact
    -0.64
    KeySpec
    -0.64
     Impact
    -0.63
     ujednoznacz
    -0.63
     Impacts
    -0.61
    WriteTagHelper
    -0.61
    NSIndexPath
    -0.60
    CGRectMake
    -0.60
    POSITIVE LOGITS
    <bos>
    0.61
    Diwedd
    0.44
    go
    0.44
    mą
    0.43
     next
    0.42
    antMatchers
    0.42
    We
    0.42
    حيح
    0.41
    istoitu
    0.41
    GTCX
    0.41
    Activations Density 1.733%

    No Known Activations