© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10184
    Prev
    Next
    INDEX
    Explanations

    phrases incorporating both "the" and terms related to the future, finances, healthcare, or strangeness

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "direction"

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

    the

    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
    Personendaten
    -0.85
    évaluateur
    -0.63
     betweenstory
    -0.61
     समीक्षाएं
    -0.59
    >--}}
    -0.53
    TextAppearance
    -0.53
    BeginContext
    -0.50
    enapa
    -0.50
     Chwiliwch
    -0.50
    ponym
    -0.50
    POSITIVE LOGITS
     direction
    1.60
    direction
    1.30
     Direction
    1.27
     directions
    1.27
    Direction
    1.15
     DIRECTION
    1.09
    directions
    1.04
     Directions
    0.99
     direção
    0.97
     direzione
    0.95
    Activations Density 1.052%

    No Known Activations