© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    the string "Gro", often followed by "k", within a short distance of another capitalized word or sentence break

    oai_token-act-pair · 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
    jangkau
    -0.54
     front
    -0.52
     disambiguazione
    -0.50
     Interpolation
    -0.49
     quæ
    -0.48
     interpolation
    -0.47
     trajets
    -0.47
     raiſ
    -0.47
     crdi
    -0.46
     retroactive
    -0.45
    POSITIVE LOGITS
     ***!
    0.59
    \{\\
    0.59
     CreateTagHelper
    0.52
    cotta
    0.52
    Enllaços
    0.51
    cyte
    0.51
    StoryboardSegue
    0.50
    XmlEnum
    0.50
    textTheme
    0.50
    linen
    0.50
    Activations Density 4.646%

    No Known Activations