© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5983
    Prev
    Next
    INDEX
    Explanations

    the word "depth" or the phrase "in order."

    oai_token-act-pair · gemini-2.0-flash

    in-depth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     CURIAM
    -0.91
    CloseOperation
    -0.85
     المعيارى
    -0.84
    RenderAtEndOf
    -0.82
     Audiodateien
    -0.82
    setVerticalGroup
    -0.78
    IsMutable
    -0.75
     îna
    -0.75
     kasarigan
    -0.74
    ArgumentParser
    -0.69
    POSITIVE LOGITS
    <bos>
    0.63
     organisation
    0.59
    authorised
    0.58
     favourite
    0.56
     programme
    0.55
    favourite
    0.55
    organisation
    0.54
     optimised
    0.54
     recognisable
    0.53
     personalised
    0.52
    Activations Density 0.832%

    No Known Activations