© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4430
    Prev
    Next
    INDEX
    Explanations

    the general topic of age

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'age'

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

    age

    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
     itſelf
    -1.06
     myſelf
    -1.00
     himſelf
    -0.87
     Efq
    -0.86
     themſelves
    -0.84
    WithIOException
    -0.84
     poffe
    -0.82
    ſelf
    -0.81
    AddTagHelper
    -0.79
     whoſe
    -0.79
    POSITIVE LOGITS
     Ver
    0.50
    forth
    0.48
     var
    0.48
     :
    0.47
     no
    0.46
     No
    0.45
     Pr
    0.45
    rrggbb
    0.44
     Ku
    0.44
     my
    0.43
    Activations Density 3.057%

    No Known Activations