© 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. 12273
    Prev
    Next
    INDEX
    Explanations

    ratios between two numbers and related financial wording

    oai_token-act-pair · gemini-2.0-flash

    to/at

    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
    RenderAtEndOf
    -1.26
     متعلقه
    -1.21
    InjectAttribute
    -1.15
     صوتيه
    -1.13
    expandindo
    -1.13
     nakalista
    -1.12
    +#+
    -1.09
    IntoConstraints
    -1.08
     doInBackground
    -1.07
    TagMode
    -1.06
    POSITIVE LOGITS
     a
    0.57
     above
    0.55
     around
    0.48
     
    0.47
     just
    0.47
     over
    0.43
     compi
    0.42
    .
    0.41
     close
    0.41
     c
    0.41
    Activations Density 11.877%

    No Known Activations