© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13278
    Prev
    Next
    INDEX
    Explanations

    words related to fishing trips or ocean excursions

    oai_token-act-pair · gemini-2.0-flash

    terms related to fishing

    np_token-act-pair-logits · gpt-4o-mini

    Fishing and sharks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     كومونز
    -0.73
    HomeAsUpEnabled
    -0.63
     AttributeSet
    -0.63
    entant
    -0.60
    endpush
    -0.60
    Бахар
    -0.59
    ✨:
    -0.59
     муніципалі
    -0.59
     transitive
    -0.58
    Obrázky
    -0.57
    POSITIVE LOGITS
    Structure
    0.57
     Structure
    0.55
     structure
    0.54
     Fische
    0.50
    launch
    0.48
    providedIn
    0.48
     launch
    0.47
     STRUCTURE
    0.47
     poissons
    0.46
    führ
    0.46
    Activations Density 0.791%

    No Known Activations