© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11458
    Prev
    Next
    INDEX
    Explanations

    scientific or technical language related to chemical processes.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     deberes
    -0.45
    ahu
    -0.42
     Simplicity
    -0.41
    ת
    -0.40
     discretization
    -0.39
     secco
    -0.38
    itemize
    -0.38
     Lösungs
    -0.37
     picha
    -0.37
    Frame
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.96
    tvguidetime
    0.83
    Билгалдахарш
    0.79
    AndEndTag
    0.76
    BeginInit
    0.71
     Савезне
    0.68
     дописавши
    0.66
    Autoritní
    0.66
    credit
    0.65
    DockStyle
    0.65
    Activations Density 4.182%

    No Known Activations