© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14278
    Prev
    Next
    INDEX
    Explanations

    words with certain suffixes, especially those ending in "ly", and also some words related to food and games.

    oai_token-act-pair · gemini-2.0-flash

    forms of "put"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     knex
    -0.63
    __*/
    -0.59
    gonic
    -0.53
     Ensemble
    -0.53
    DockStyle
    -0.53
     ensemble
    -0.50
     assembly
    -0.50
    !*\
    -0.49
     uska
    -0.47
    важа
    -0.46
    POSITIVE LOGITS
     put
    2.59
    Put
    2.45
     Put
    2.42
    put
    2.39
     PUT
    2.14
    Putting
    2.11
     Putting
    2.09
     puts
    2.06
     putting
    2.05
    putting
    1.87
    Activations Density 4.041%

    No Known Activations