© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4845
    Prev
    Next
    INDEX
    Explanations

    places where someone is putting something (especially money or resources) into a specific, larger context

    oai_token-act-pair · gemini-2.0-flash

    context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    __(/*!
    -0.57
    findpost
    -0.55
    bitField
    -0.54
    AndEndTag
    -0.52
    :✨
    -0.52
    AutoField
    -0.46
     Dinosaur
    -0.45
     Tig
    -0.43
     Hochschule
    -0.43
     Şi
    -0.43
    POSITIVE LOGITS
     context
    2.02
     Context
    1.77
    context
    1.77
    Context
    1.61
     contexto
    1.55
     CONTEXT
    1.49
     perspective
    1.47
     contexte
    1.45
     contex
    1.42
     contextual
    1.40
    Activations Density 0.950%

    No Known Activations