© 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. 1622
    Prev
    Next
    INDEX
    Explanations

    a variety of positive indicators or connectors of value or relationship regardless of domain.

    oai_token-act-pair · gemini-2.0-flash

    access, gain

    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
     constant
    -1.22
     frequent
    -1.22
    frequent
    -1.16
     Frequent
    -1.16
     rapid
    -1.14
    constant
    -1.11
     continual
    -1.06
    Frequent
    -1.05
     gradual
    -1.03
     costante
    -1.03
    POSITIVE LOGITS
    ConstraintMaker
    0.78
    RectangleBorder
    0.68
    Tembelea
    0.59
    WriteBarrier
    0.56
     otomatig
    0.54
    ReusableCell
    0.54
    áját
    0.53
     BnF
    0.53
    mability
    0.52
    MLLoader
    0.51
    Activations Density 5.323%

    No Known Activations