© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    statements that include the word "think" along with related words like recognizing, believe, and thought.

    oai_token-act-pair · gemini-2.0-flash

    think

    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
     disambiguazione
    -1.13
     raiſ
    -1.13
     itſelf
    -1.12
     pleaſure
    -1.05
     doubtnut
    -1.03
     Majefty
    -1.00
     Monfieur
    -0.97
    DockStyle
    -0.96
     myſelf
    -0.95
    ſelf
    -0.94
    POSITIVE LOGITS
     
    0.48
    身
    0.41
     B
    0.40
    ANTLR
    0.40
     mañana
    0.39
     Q
    0.38
     sei
    0.37
     Z
    0.37
     d
    0.37
     (
    0.36
    Activations Density 0.459%

    No Known Activations