© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2773
    Prev
    Next
    INDEX
    Explanations

    HTML code and structural elements or formatting

    oai_token-act-pair · gemini-2.0-flash

    code/markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ^(@)
    -0.63
     vents
    -0.61
     apartments
    -0.60
     reparations
    -0.58
     exciter
    -0.57
     perfons
    -0.57
     bungalows
    -0.56
     lugs
    -0.56
     postpartum
    -0.56
     wetting
    -0.56
    POSITIVE LOGITS
     doInBackground
    0.74
    twimg
    0.61
     /\.
    0.59
    pushFollow
    0.56
     NSCoder
    0.56
    bnf
    0.56
    UIControlState
    0.56
    SequentialGroup
    0.55
    IonicModule
    0.54
     "
    0.54
    Activations Density 6.242%

    No Known Activations