© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to writing, publishing arts and entertainment generally as well as technical programming terms.

    oai_token-act-pair · gemini-2.0-flash

    writings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ujednoznacz
    -0.60
     all
    -0.52
    bit
    -0.49
     bocas
    -0.47
    +#+#
    -0.47
    الإنجليزية
    -0.46
    orsk
    -0.46
    all
    -0.46
     tutte
    -0.43
    ี่ย
    -0.43
    POSITIVE LOGITS
     itſelf
    1.10
     myſelf
    0.86
     himſelf
    0.83
     againſt
    0.81
     theſe
    0.81
     whoſe
    0.80
     Baillargeon
    0.79
     raiſ
    0.78
     Theſe
    0.77
    principalColumn
    0.76
    Activations Density 11.862%

    No Known Activations