© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3514
    Prev
    Next
    INDEX
    Explanations

    verbs used to describe actions or speech in a narrative

    oai_token-act-pair · gemini-2.0-flash

    narrative dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    قایناق‌لار
    -0.68
     saites
    -0.66
     المعيارى
    -0.62
    webElementGuid
    -0.60
     otomatig
    -0.60
    +#+#
    -0.59
    AccessorTable
    -0.58
    Datuak
    -0.57
    oa̍t
    -0.56
     noDo
    -0.55
    POSITIVE LOGITS
     Roskov
    0.63
    oban
    0.56
    uri
    0.54
    TimeSpan
    0.53
    ivably
    0.52
    ghal
    0.50
    новништво
    0.49
    haba
    0.48
    Marshall
    0.48
    OrBuilder
    0.48
    Activations Density 5.447%

    No Known Activations