© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13009
    Prev
    Next
    INDEX
    Explanations

    code documentation comments

    oai_token-act-pair · gemini-2.0-flash

    math and dimensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    featureID
    -0.93
    GEBURTSDATUM
    -0.91
     ostavi
    -0.87
     Савезне
    -0.86
    曖昧さ回避
    -0.85
    iastes
    -0.81
     يتيمه
    -0.81
     الحره
    -0.80
    RTEE
    -0.79
     linkovi
    -0.79
    POSITIVE LOGITS
     d
    0.51
     D
    0.47
    γη
    0.46
    TabIndex
    0.44
    fan
    0.43
     in
    0.43
    сион
    0.42
    d
    0.42
    el
    0.42
     fan
    0.41
    Activations Density 2.105%

    No Known Activations