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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8083
    Prev
    Next
    INDEX
    Explanations

    words associated with thinking, considering, knowledge and understanding

    oai_token-act-pair · gemini-2.0-flash

    think

    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
     think
    -0.54
     pensamiento
    -0.50
     thinks
    -0.50
     pensiero
    -0.48
     thought
    -0.47
    R
    -0.47
     uñas
    -0.47
     thinking
    -0.46
     pensée
    -0.46
    lardır
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.94
     nahilalakip
    0.82
     SafeMath
    0.65
     ComVisible
    0.65
     محفوظة
    0.64
    __':
    0.63
    hability
    0.62
     of
    0.61
    enumii
    0.61
    ########.
    0.61
    Activations Density 12.365%

    No Known Activations