© 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. 15238
    Prev
    Next
    INDEX
    Explanations

    passages involving parents or family, and in at least one passage, loneliness.

    oai_token-act-pair · gemini-2.0-flash

    dad

    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
     Efq
    -1.15
     quæ
    -1.09
     ſtate
    -1.09
     whoſe
    -1.09
     étoient
    -1.07
     myſelf
    -1.05
     avoient
    -1.05
     becauſe
    -1.05
     Theſe
    -1.04
     Monfieur
    -1.04
    POSITIVE LOGITS
    ,
    0.74
    prefixer
    0.72
    <bos>
    0.65
    ↵↵
    0.58
    .
    0.57
    '
    0.56
     tủ
    0.56
    ;
    0.55
    -
    0.54
    :
    0.54
    Activations Density 0.938%

    No Known Activations