© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3767
    Prev
    Next
    INDEX
    Explanations

    references to political governors

    oai_token-act-pair · gemini-2.0-flash

    government positions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hyper
    -0.60
     Hyper
    -0.59
    modelBuilder
    -0.55
    Hyper
    -0.54
     Internet
    -0.53
     master
    -0.51
    blan
    -0.51
    vart
    -0.49
     real
    -0.49
     reverse
    -0.49
    POSITIVE LOGITS
    saraba
    0.70
    ंदीखरीदारी
    0.68
    tvguidetime
    0.65
    verwijspagina
    0.64
     ujednoznacz
    0.58
    <()>
    0.57
     esternos
    0.55
    TextSpan
    0.54
    RUnlock
    0.54
    +#+#
    0.53
    Activations Density 0.441%

    No Known Activations