© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    words referring to a series of steps or an ordered process.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming concepts

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

    steps in a process

    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
    publique
    -0.52
    zyw
    -0.50
    Шаг
    -0.50
    repositories
    -0.49
    Ско
    -0.49
     Areas
    -0.47
    addCriterion
    -0.47
     Совета
    -0.47
    hame
    -0.46
    Areas
    -0.45
    POSITIVE LOGITS
    kháu
    0.87
    UrlResolution
    0.71
     endwhile
    0.70
    ]")]
    0.69
    parsedMessage
    0.69
    MigrationBuilder
    0.68
    StoryboardSegue
    0.67
     <=",
    0.66
     мѣ
    0.66
    EndGlobalSection
    0.65
    Activations Density 3.446%

    No Known Activations