© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15111
    Prev
    Next
    INDEX
    Explanations

    descriptions of painting miniatures with metallic paints and washes, with a focus on weathering and highlighting.

    oai_token-act-pair · gemini-2.0-flash

    Art and painting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    EndGlobalSection
    -0.52
    lelő
    -0.52
    Synonymes
    -0.51
     geslacht
    -0.46
    GPC
    -0.44
    جل
    -0.44
    eqn
    -0.43
    دانشنامهٔ
    -0.43
    谐
    -0.42
     authority
    -0.42
    POSITIVE LOGITS
    ArgsConstructor
    0.81
    endpush
    0.75
    TagMode
    0.68
    onets
    0.58
    躇
    0.57
    agramm
    0.51
    zehn
    0.51
    EndContext
    0.50
     RISERVATA
    0.50
    opener
    0.49
    Activations Density 1.712%

    No Known Activations