© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2536
    Prev
    Next
    INDEX
    Explanations

    adjectival phrases with intensifiers

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     distanciation
    -0.50
    országban
    -0.49
    icali
    -0.48
    MathML
    -0.47
    ()]);
    -0.46
    rophobic
    -0.45
    </caption>
    -0.44
    望
    -0.44
     };
    -0.44
    ]}\
    -0.43
    POSITIVE LOGITS
     cherchés
    0.73
    цездатний
    0.69
    Билгалдахарш
    0.69
    UserScript
    0.68
     coscienza
    0.67
     abbildung
    0.64
    GEBURTSDATUM
    0.64
    findpost
    0.63
    webElementXpaths
    0.63
     Agamemnon
    0.63
    Activations Density 2.252%

    No Known Activations