© 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. 14175
    Prev
    Next
    INDEX
    Explanations

    words that appear in numbered lists or indicate a level of skill ("level 1") or that signify rank or hierarchy ("Chief Executive") or measure quality ("best seller").

    oai_token-act-pair · gemini-2.0-flash

    Random topics

    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
    -1.46
    theless
    -1.45
    ization
    -1.45
    neath
    -1.38
    imed
    -1.25
    time
    -1.24
    selves
    -1.24
    poptosis
    -1.22
    fraid
    -1.21
    queous
    -1.20
    POSITIVE LOGITS
    ponym
    0.68
    ouille
    0.65
    Jeografia
    0.59
    obox
    0.57
    phro
    0.56
    taxia
    0.56
    tubers
    0.55
    ramid
    0.55
    mless
    0.54
    lider
    0.54
    Activations Density 18.276%

    No Known Activations