© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    text relating to legal proceedings and technical documentation, potentially within code or specifications.

    oai_token-act-pair · gemini-2.0-flash

    Section references (Sec)

    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
     pe
    -1.00
     ra
    -1.00
     ab
    -0.95
     sa
    -0.93
     se
    -0.91
     bel
    -0.91
     har
    -0.90
     ru
    -0.90
     che
    -0.90
     en
    -0.89
    POSITIVE LOGITS
     feroit
    1.23
     avoient
    1.19
     auroit
    1.17
     étoient
    1.15
     vectorielles
    1.14
     étoit
    1.13
     mijne
    1.09
     pouvoit
    1.09
     bēr
    1.08
     enfans
    1.08
    Activations Density 56.352%

    No Known Activations