© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3000
    Prev
    Next
    INDEX
    Explanations

    words related to writing, speaking, official actions, academia, money or groups of people.

    oai_token-act-pair · gemini-2.0-flash

    creation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     tartalmaz
    -0.46
     klara
    -0.46
    ayev
    -0.46
    juga
    -0.45
     Rien
    -0.45
    illère
    -0.44
    ceğini
    -0.44
    Rien
    -0.43
    érées
    -0.43
     profiter
    -0.43
    POSITIVE LOGITS
     created
    1.31
     creation
    1.29
     formation
    1.28
     forming
    1.26
     formed
    1.24
     Created
    1.07
     Forming
    1.07
     constructing
    1.07
     constructed
    1.07
     create
    1.06
    Activations Density 4.935%

    No Known Activations