© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12875
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing, particularly identifying colors and apparel types

    oai_token-act-pair · gemini-2.0-flash

    clothing descriptions

    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
     NavController
    -0.53
    providedIn
    -0.52
    )]);
    -0.52
     adipis
    -0.51
    PPC
    -0.45
    횟
    -0.45
    findOrFail
    -0.44
    ariConfig
    -0.44
    queryInterface
    -0.43
    Personendaten
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    TagMode
    0.64
    gdx
    0.62
    NewUrlParser
    0.57
    collegiate
    0.56
     territoriale
    0.53
     Ause
    0.53
     groaned
    0.53
    qrstuvwxyz
    0.52
    pañol
    0.52
    Activations Density 4.721%

    No Known Activations