© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    years, especially 2000-2011

    oai_token-act-pair · gemini-2.0-flash

    numerical patterns and specific data entries

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

    Code and dates

    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
     surla
    -0.77
    ⓧ
    -0.69
    #+#
    -0.68
    ніципа
    -0.68
    ViewFeatures
    -0.66
    ApiModelProperty
    -0.64
     CanadaChoose
    -0.64
    djangoproject
    -0.64
    ьаж
    -0.57
     متعلقه
    -0.57
    POSITIVE LOGITS
    1
    0.49
    囗
    0.48
     thither
    0.46
     tubercle
    0.46
     hydrostatic
    0.46
    Kreis
    0.45
    omaterials
    0.43
    2
    0.43
    enciaga
    0.43
     Commune
    0.42
    Activations Density 0.536%

    No Known Activations