© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    references to science fiction or fantasy battles

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Science fiction

    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
    thâu
    -0.59
     égard
    -0.49
     tục
    -0.48
    wußt
    -0.47
    Extinguishing
    -0.46
    AsUp
    -0.44
    quisites
    -0.40
     skola
    -0.39
    uttore
    -0.39
    ocyclic
    -0.39
    POSITIVE LOGITS
     jadx
    0.67
    tvguidetime
    0.63
     initComponents
    0.62
    antMatchers
    0.60
     kasarigan
    0.59
    ClInclude
    0.58
    ंदीखरीदारी
    0.58
    GraphicsUnit
    0.56
    CUS
    0.56
     TextInputType
    0.56
    Activations Density 1.097%

    No Known Activations