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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    words related to color and weathering effects, potentially in the context of miniatures or model painting.

    oai_token-act-pair · gemini-2.0-flash

    describing appearance

    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
     Colour
    -0.65
     couleur
    -0.64
     Farbe
    -0.61
     colour
    -0.61
     colore
    -0.59
    Colour
    -0.59
     couleurs
    -0.59
    rinfo
    -0.59
    colour
    -0.58
     COLOUR
    -0.58
    POSITIVE LOGITS
    ⓧ
    0.68
     Normdatei
    0.57
    thalam
    0.57
     a
    0.56
     contextLoads
    0.56
    expandindo
    0.53
    postIndex
    0.52
    keyColumn
    0.51
    parsedMessage
    0.50
    oges
    0.50
    Activations Density 4.442%

    No Known Activations