© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11343
    Prev
    Next
    INDEX
    Explanations

    words in all caps having to do with strong concepts/actions

    oai_token-act-pair · gemini-2.0-flash

    code fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ks
    -0.68
    ate
    -0.62
    rom
    -0.59
    z
    -0.59
    un
    -0.59
    tr
    -0.59
    ut
    -0.58
    ank
    -0.58
    ons
    -0.57
    fe
    -0.57
    POSITIVE LOGITS
    latego
    0.67
    RegressionTest
    0.66
    anskje
    0.66
     onBackPressed
    0.64
    帖最后由
    0.64
     nahilalakip
    0.63
    
    0.62
    OOTD
    0.62
     nemlig
    0.61
    polation
    0.60
    Activations Density 0.943%

    No Known Activations