© 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. 11948
    Prev
    Next
    INDEX
    Explanations

    the word "utility" and words associated with value

    oai_token-act-pair · gemini-2.0-flash

    utility

    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
    <bos>
    -1.40
     Monfieur
    -0.95
     ainfi
    -0.94
     étoit
    -0.92
     auffi
    -0.91
     CanadaChoose
    -0.88
     ſtand
    -0.84
     foncé
    -0.83
     Jefus
    -0.83
     acrylique
    -0.81
    POSITIVE LOGITS
     "<?
    0.69
    ]';
    0.67
     Lad
    0.58
     />);
    0.57
    sted
    0.56
     newUser
    0.55
    konos
    0.54
    erol
    0.53
     à
    0.52
     La
    0.52
    Activations Density 1.233%

    No Known Activations