© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12649
    Prev
    Next
    INDEX
    Explanations

    words with negative connotations that relate to problems, like risks, warnings, and unwanted effects

    oai_token-act-pair · gemini-2.0-flash

    words related to technology or applications

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

    programs

    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
    seamnă
    -0.70
     laiton
    -0.66
     oreilles
    -0.63
     varandra
    -0.62
    脚注の使い方
    -0.62
     nuages
    -0.62
     conseguenze
    -0.60
     poussière
    -0.60
     ouvriers
    -0.60
    tahankan
    -0.59
    POSITIVE LOGITS
     program
    0.69
     device
    0.69
     vessel
    0.68
     prog
    0.65
     application
    0.64
     item
    0.64
     procedure
    0.63
     vehicle
    0.63
     programme
    0.63
     theme
    0.59
    Activations Density 7.726%

    No Known Activations