© 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. 13166
    Prev
    Next
    INDEX
    Explanations

    square brackets containing numbers

    oai_token-act-pair · gemini-2.0-flash

    ]

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ."]
    -1.34
     ―――――
    -1.32
    tagHelperRunner
    -1.27
     Efq
    -1.27
     auffi
    -1.25
     iſt
    -1.25
    principalColumn
    -1.24
     disambiguazione
    -1.22
    ^(@)
    -1.20
     ་་
    -1.19
    POSITIVE LOGITS
    [toxicity=0]
    2.03
    ↵↵
    1.70
    ↵
    1.28
    ↵↵↵
    1.18
    <eos>
    1.14
    ↵↵↵↵
    0.97
      
    0.94
    ↵↵↵↵↵
    0.88
     I
    0.81
    ↵↵↵↵↵↵
    0.78
    Activations Density 0.140%

    No Known Activations