© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1925
    Prev
    Next
    INDEX
    Explanations

    words related to energy companies and billing

    oai_token-act-pair · gemini-2.0-flash

    words related to energy supply and consumption

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

    Financial news

    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
     AssemblyTitle
    -0.99
    endphp
    -0.81
    posedge
    -0.74
    Hochspringen
    -0.73
    fromCharCode
    -0.72
    extAlignment
    -0.70
    SpringBootTest
    -0.68
    XDECREF
    -0.66
    ✨:
    -0.65
    estacks
    -0.65
    POSITIVE LOGITS
    TargetApi
    0.54
    плот
    0.44
    ┻
    0.43
    berti
    0.41
    onan
    0.41
     سرد
    0.39
    asa
    0.39
    ruk
    0.39
     бъде
    0.38
    di
    0.38
    Activations Density 0.592%

    No Known Activations