© 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. 7497
    Prev
    Next
    INDEX
    Explanations

    the word "up" or verbs that mean to uncover or make accessible

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "up"

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

    say up

    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
    -0.68
    ThroughAttribute
    -0.55
    حياته
    -0.52
     ModelExpression
    -0.50
    OGND
    -0.49
     MotionEvent
    -0.49
     dAtA
    -0.48
    ">//
    -0.47
    حياتها
    -0.47
    PreferredItem
    -0.46
    POSITIVE LOGITS
     up
    3.00
     Up
    2.05
    up
    2.00
    Up
    1.96
     UP
    1.55
     upto
    1.30
    UP
    1.30
     lên
    1.27
    アップ
    1.25
    ups
    1.21
    Activations Density 1.410%

    No Known Activations