© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9522
    Prev
    Next
    INDEX
    Explanations

    parts of words that often indicate a country of origin or region

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    VIAF
    -0.46
    ↵
    -0.44
    מט
    -0.43
     sta
    -0.43
     Cor
    -0.41
    aura
    -0.41
    ↵↵
    -0.40
    DBNull
    -0.40
    '
    -0.40
    cau
    -0.39
    POSITIVE LOGITS
     Normdatei
    0.78
    protoimpl
    0.73
    __);
    0.69
     fhort
    0.67
    thâu
    0.65
    :]:
    0.64
    tiness
    0.64
    ]")]
    0.63
    }}}
    0.63
    =$?
    0.61
    Activations Density 3.029%

    No Known Activations