Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7849
    Prev
    Next
    INDEX
    Explanations

    words related to the dimensions or layout of a chart or graph

    oai_token-act-pair · gemini-2.0-flash

    height

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     height
    -2.78
     Height
    -2.47
    height
    -2.44
    Height
    -2.36
     HEIGHT
    -2.16
     heights
    -2.14
    HEIGHT
    -1.93
     altura
    -1.77
    heights
    -1.46
     hauteur
    -1.40
    POSITIVE LOGITS
    +#+#
    0.67
    mappedBy
    0.60
    AutoField
    0.59
    IsMutable
    0.59
     kasarigan
    0.59
     numberWith
    0.59
    lwjgl
    0.58
    UIControlState
    0.54
     doInBackground
    0.54
    numerusform
    0.52
    Activations Density 4.283%

    No Known Activations