© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7120
    Prev
    Next
    INDEX
    Explanations

    the words "hands" and "head".

    oai_token-act-pair · gemini-2.0-flash

    body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Reſ
    -0.90
    Nuorodos
    -0.84
    Зноскі
    -0.84
     resourceCulture
    -0.82
     Houſe
    -0.81
    stateProvider
    -0.80
     étoit
    -0.80
     Theſe
    -0.79
     iſt
    -0.79
    RenderAtEndOf
    -0.79
    POSITIVE LOGITS
    -
    0.51
     in
    0.48
     me
    0.40
     full
    0.39
     r
    0.39
     open
    0.38
     on
    0.38
     L
    0.37
     e
    0.36
     five
    0.36
    Activations Density 0.330%

    No Known Activations