© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    words that involve the action of something being shown

    oai_token-act-pair · gemini-2.0-flash

    reflect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     reflection
    -1.30
     reflect
    -1.23
     reflecting
    -1.19
     Reflect
    -1.15
    reflection
    -1.13
     reflections
    -1.13
     Reflection
    -1.09
    reflect
    -1.07
    Reflect
    -1.02
     reflects
    -1.00
    POSITIVE LOGITS
    تقاوى
    0.63
    ########.
    0.61
    DoubleQuotes
    0.60
     nahilalakip
    0.55
    ]")]
    0.55
    fcntl
    0.53
    AndPassword
    0.53
     azzurro
    0.51
     FirebaseAuth
    0.50
     }</
    0.50
    Activations Density 33.936%

    No Known Activations