© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    a smattering of common verbs and article-noun pairings.

    oai_token-act-pair · gemini-2.0-flash

    Forms of "every"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     fallu
    -0.43
    leştir
    -0.42
     Administrativna
    -0.41
    isson
    -0.38
    presto
    -0.36
    売
    -0.36
    lops
    -0.35
    ObjectType
    -0.34
     feu
    -0.34
    jutkan
    -0.34
    POSITIVE LOGITS
     every
    2.91
    every
    2.70
    Every
    2.42
     Every
    2.39
     EVERY
    1.82
     ogni
    1.82
    EVERY
    1.74
     setiap
    1.65
     κάθε
    1.53
    Setiap
    1.51
    Activations Density 3.122%

    No Known Activations