© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1552
    Prev
    Next
    INDEX
    Explanations

    instructions and information about tools and processes for crafting and manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    sewing patterns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Референце
    -0.70
    ThroughAttribute
    -0.67
    +#+#
    -0.64
    GEBURTSDATUM
    -0.64
     "..\..\..\
    -0.61
    VersionUID
    -0.61
    localctx
    -0.59
    ftagPool
    -0.59
     للمعارف
    -0.57
     ProtoMessage
    -0.57
    POSITIVE LOGITS
    ும்
    0.49
    CCN
    0.47
    iestety
    0.47
    velt
    0.46
     blink
    0.46
    csname
    0.46
    UNC
    0.45
    Fl
    0.45
    asure
    0.45
    $_.
    0.44
    Activations Density 3.390%

    No Known Activations