© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    words beginning with "ren" or containing "sn"

    oai_token-act-pair · gemini-2.0-flash

    say "sn" words

    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
     <<<<<<<<<<<<<<
    -0.80
     pinulongan
    -0.75
     nahilalakip
    -0.66
     تضيفلها
    -0.66
     propOrder
    -0.65
    kuuta
    -0.64
     mergeFrom
    -0.64
    tagHelper
    -0.62
     Administrativna
    -0.62
    addPreferredGap
    -0.61
    POSITIVE LOGITS
    ar
    0.52
    es
    0.43
     arm
    0.40
    inge
    0.39
    inc
    0.39
    ⓘ
    0.38
     Arm
    0.38
    arle
    0.37
    ########.
    0.37
    ry
    0.36
    Activations Density 0.607%

    No Known Activations