© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14165
    Prev
    Next
    INDEX
    Explanations

    the word "gift", and sometimes words related to public recognition, the possessive "my," or publicizing something

    oai_token-act-pair · gemini-2.0-flash

    gift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    homonymie
    -0.70
    fetchone
    -0.63
    xically
    -0.59
     cal
    -0.59
     Attorneys
    -0.59
    ittà
    -0.59
     Middleton
    -0.57
    callee
    -0.57
    írito
    -0.57
    ctez
    -0.57
    POSITIVE LOGITS
     Efq
    1.04
     Diſ
    1.00
     Houſe
    0.98
     Anſ
    0.98
     Reſ
    0.97
     Conſ
    0.97
     fileSize
    0.90
     Theſe
    0.89
     ―――――
    0.89
     $_(
    0.88
    Activations Density 3.051%

    No Known Activations