© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    words related to underlying, inherent characteristics

    oai_token-act-pair · gemini-2.0-flash

    nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     يتيمه
    -0.93
    tonsoft
    -0.74
    toMatchSnapshot
    -0.66
     getItemId
    -0.66
    contentLoaded
    -0.64
     Efq
    -0.62
     quæ
    -0.58
     ModelAndView
    -0.58
     Quid
    -0.57
    ئه
    -0.57
    POSITIVE LOGITS
     inherently
    0.62
     nature
    0.51
    天生
    0.46
     lik
    0.44
     viewType
    0.42
    性質
    0.42
     NATURE
    0.41
     capac
    0.41
     nahilalakip
    0.40
    IsContent
    0.40
    Activations Density 2.462%

    No Known Activations