© 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. 13848
    Prev
    Next
    INDEX
    Explanations

    the number 9 followed by a number 1, 2, 3, 5, 6, 7 or 8

    oai_token-act-pair · gemini-2.0-flash

    numeric and date references

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

    9

    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
     Normdatei
    -0.93
     CanadaChoose
    -0.80
     économies
    -0.71
    tvguidetime
    -0.70
     dieux
    -0.69
    RUCT
    -0.67
    InjectAttribute
    -0.66
     églises
    -0.65
    رشف
    -0.65
    djangoproject
    -0.65
    POSITIVE LOGITS
     March
    0.47
    1
    0.47
    2
    0.47
    0
    0.47
    sa
    0.46
     sp
    0.45
    do
    0.44
     mar
    0.43
    erek
    0.43
     snap
    0.42
    Activations Density 0.926%

    No Known Activations