© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2738
    Prev
    Next
    INDEX
    Explanations

    numbers that are either an exact or approximate count of something

    oai_token-act-pair · gemini-2.0-flash

    non-standard terms or patterns

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

    0

    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
    MigrationBuilder
    -0.78
    󠁿
    -0.77
    expandindo
    -0.76
     poveznice
    -0.74
     CreateTagHelper
    -0.72
    InjectAttribute
    -0.72
     يتيمه
    -0.72
    principalColumn
    -0.70
    aarrggbb
    -0.69
    IntoConstraints
    -0.68
    POSITIVE LOGITS
    +#+#
    0.47
    atari
    0.43
     acc
    0.41
    ত্ত
    0.41
    udesta
    0.40
     jakim
    0.40
    MAXIMUM
    0.39
     supers
    0.39
    mith
    0.39
     dak
    0.39
    Activations Density 4.089%

    No Known Activations