© 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. 4688
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe things.

    oai_token-act-pair · gemini-2.0-flash

    complex, interesting topics

    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
     članak
    -0.59
     datter
    -0.51
     Halls
    -0.48
     resourceCulture
    -0.46
    Varint
    -0.45
    lante
    -0.45
     Penga
    -0.45
     propOrder
    -0.43
    pendente
    -0.42
    átek
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.81
    mybatisplus
    0.79
    UIControlState
    0.75
    NUMX
    0.68
    HostException
    0.64
    MediaStore
    0.63
    />";
    0.62
    AndEndTag
    0.60
    (@"%@",
    0.59
    "):
    0.57
    Activations Density 9.922%

    No Known Activations