© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15700
    Prev
    Next
    INDEX
    Explanations

    a variety of words loosely related to articles, prepositions, and certain words of Germanic origin.

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    merate
    -0.63
    IZABETH
    -0.62
    HtmlAttribute
    -0.60
    ]--;
    -0.59
    ResumeLayout
    -0.58
     вікі
    -0.58
    URBANA
    -0.56
    новниш
    -0.54
    AutoScaleMode
    -0.54
     Lightboxes
    -0.52
    POSITIVE LOGITS
     betweenstory
    0.55
    racene
    0.52
     courrier
    0.51
    Protos
    0.50
     priori
    0.49
    endpush
    0.47
    っこう
    0.47
    好事
    0.46
    ţin
    0.44
    zellen
    0.44
    Activations Density 38.005%

    No Known Activations