© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15236
    Prev
    Next
    INDEX
    Explanations

    words that express negation, absence, or low quantity

    oai_token-act-pair · gemini-2.0-flash

    authenticity and substance

    np_token-act-pair-logits · gpt-4o-mini

    genuineness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ArrowToggle
    -0.39
     rarement
    -0.35
     esta
    -0.35
    ば
    -0.34
     por
    -0.34
     cuarzo
    -0.34
     című
    -0.34
     ?></
    -0.34
     généralement
    -0.33
     aján
    -0.33
    POSITIVE LOGITS
     real
    1.28
     meaningful
    1.23
     genuine
    1.16
     substantive
    1.16
     REAL
    1.15
    real
    1.12
     reale
    1.09
     actual
    1.08
     echte
    1.07
     true
    1.06
    Activations Density 3.615%

    No Known Activations