© 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. 10991
    Prev
    Next
    INDEX
    Explanations

    strings resembling dates, numbers, times, URLs, or XML tags

    oai_token-act-pair · gemini-2.0-flash

    Numbers above seven

    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
    riwal
    -0.51
     AspNetCore
    -0.48
    Portail
    -0.48
    HideFlags
    -0.42
    ؤية
    -0.40
    Cyfeiriadau
    -0.38
    UrlResolution
    -0.36
    IsContent
    -0.35
     برانيه
    -0.34
    <0x85>
    -0.33
    POSITIVE LOGITS
     nine
    1.89
     eight
    1.86
     Eight
    1.76
     eighth
    1.73
    8
    1.72
     ninth
    1.69
     Nine
    1.64
     Eighth
    1.63
    9
    1.61
     EIGHT
    1.59
    Activations Density 17.680%

    No Known Activations