© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7453
    Prev
    Next
    INDEX
    Explanations

    words that appear to mark a distinct clause or topic shift

    oai_token-act-pair · gemini-2.0-flash

    turn variants

    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
     ModelExpression
    -0.54
     препратки
    -0.54
    Erstellt
    -0.53
    findpost
    -0.52
    ContentAsync
    -0.51
    AndroidJUnit
    -0.50
    UnsafeEnabled
    -0.49
     MenuView
    -0.47
    Билгалдахарш
    -0.46
     متعلقه
    -0.46
    POSITIVE LOGITS
     turn
    2.91
     Turn
    2.72
    turn
    2.70
     turning
    2.69
    Turn
    2.66
     turned
    2.63
     turns
    2.50
     Turning
    2.47
    turning
    2.45
     TURN
    2.44
    Activations Density 7.348%

    No Known Activations