© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5766
    Prev
    Next
    INDEX
    Explanations

    sections of writing where the author is building an argument or making a point by using conjunctions, qualifications, or explanations

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     but
    -2.98
    but
    -2.31
     But
    -2.23
    But
    -2.17
     nhưng
    -2.14
     pero
    -2.11
     tetapi
    -2.09
     BUT
    -1.98
     namun
    -1.90
     However
    -1.84
    POSITIVE LOGITS
     defaultstate
    0.89
    Datuak
    0.83
    Atsauces
    0.75
     betweenstory
    0.71
     resourceCulture
    0.69
     referenties
    0.68
     مرئيه
    0.66
    enderror
    0.63
    CppMethod
    0.62
     GenerationType
    0.62
    Activations Density 3.707%

    No Known Activations