© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15838
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes, like "anti", "pro", "re", "ing", "ed", and other short word fragments

    oai_token-act-pair · gemini-2.0-flash

    drive

    np_max-act-logits · 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
    withstanding
    -1.43
    theless
    -1.34
    neath
    -1.33
    time
    -1.27
    poptosis
    -1.23
    queous
    -1.22
    ward
    -1.22
    stairs
    -1.17
    gether
    -1.15
    currency
    -1.14
    POSITIVE LOGITS
    obox
    0.61
    нрави
    0.53
    attenzione
    0.52
    chromium
    0.50
    FormTagHelper
    0.48
    ponym
    0.48
    diğ
    0.47
     disambiguazione
    0.47
    hdys
    0.47
    AutoSize
    0.47
    Activations Density 13.227%

    No Known Activations