© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    text inside of quotation marks

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    "):
    -3.22
    "):
    -3.09
    ":
    -3.03
    '):
    -3.03
    '):
    -3.03
    "]:
    -2.94
    ']:
    -2.92
    ':
    -2.73
    ()):
    -2.66
    ')):
    -2.66
    POSITIVE LOGITS
    :
    2.53
    ;
    1.50
    -
    1.43
    ,
    1.38
    .
    1.30
    (
    1.24
      
    1.22
     
    1.20
     -
    1.18
    _
    1.18
    Activations Density 2.410%

    No Known Activations