© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10312
    Prev
    Next
    INDEX
    Explanations

    different types of media and art

    oai_token-act-pair · gemini-2.0-flash

    artistic works

    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
    forName
    -0.77
     CreateTagHelper
    -0.65
    setVerticalGroup
    -0.65
    uxxxx
    -0.63
     CanadaChoose
    -0.60
    Rujuakan
    -0.59
    Референце
    -0.58
    WindowConstants
    -0.56
    numerusform
    -0.55
    Referințe
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.53
     stone
    0.50
     film
    0.48
    BaseEntity
    0.48
     drawing
    0.47
     drawn
    0.47
    Domestic
    0.46
     domestic
    0.46
    UserInput
    0.46
     mineral
    0.46
    Activations Density 1.720%

    No Known Activations