© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7049
    Prev
    Next
    INDEX
    Explanations

    words relating to rap music, with extra attention to DJ's

    oai_token-act-pair · gemini-2.0-flash

    hip-hop related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     estekak
    -0.56
     MC
    -0.55
    ReusableCell
    -0.53
    لينكات
    -0.51
    /***/
    -0.50
    __*/
    -0.50
    Билгалдахарш
    -0.48
    tah
    -0.46
    Odkazy
    -0.46
     em
    -0.46
    POSITIVE LOGITS
     Efq
    0.82
     Jefus
    0.71
    出版年
    0.67
     iſt
    0.65
     itſelf
    0.64
    ividual
    0.63
     raiſ
    0.61
     Conform
    0.60
     Hopf
    0.60
    ſelf
    0.59
    Activations Density 0.157%

    No Known Activations