© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12970
    Prev
    Next
    INDEX
    Explanations

    words related to government, politics, and official organizations

    oai_token-act-pair · gemini-2.0-flash

    local government/health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    θος
    -0.68
     odkazy
    -0.67
    IUrlHelper
    -0.67
     Tafel
    -0.66
     insuffisamment
    -0.65
    authorities
    -0.64
     Normdatei
    -0.63
    tvguidetime
    -0.63
    Autoritní
    -0.62
    ULUS
    -0.60
    POSITIVE LOGITS
    Illuminate
    0.49
    те
    0.42
     laboral
    0.40
    CUSSION
    0.40
    cari
    0.39
    }}{(
    0.39
    нік
    0.36
    రి
    0.36
    conio
    0.36
    TE
    0.36
    Activations Density 3.861%

    No Known Activations