© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13466
    Prev
    Next
    INDEX
    Explanations

    language related to systems and also frequently flags the verb "is" and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    research paper context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     use
    -1.66
     usage
    -1.61
     utilization
    -1.55
     Use
    -1.53
     utilisation
    -1.52
     USING
    -1.52
    Use
    -1.50
     using
    -1.50
     utilizing
    -1.47
     Using
    -1.45
    POSITIVE LOGITS
    PhysRevLett
    0.51
    Lerp
    0.50
    Throwable
    0.44
    ️⃣
    0.42
    하게
    0.41
    cher
    0.41
    lné
    0.41
     infrar
    0.40
    urture
    0.40
    irmingham
    0.40
    Activations Density 2.585%

    No Known Activations