© 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. 13650
    Prev
    Next
    INDEX
    Explanations

    code snippets, links, or specific code-related terms.

    oai_token-act-pair · gemini-2.0-flash

    documents

    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
    Tipps
    -0.42
     klare
    -0.42
     Commentaires
    -0.41
    Details
    -0.41
    ovács
    -0.41
     clearness
    -0.40
     purpoſe
    -0.40
    CppMethod
    -0.39
     sacré
    -0.39
     ſche
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    0.79
     propOrder
    0.78
    ]</
    0.74
     typelib
    0.73
    enumi
    0.69
     ]
    0.68
     تضيفلها
    0.68
    HtmlAttribute
    0.68
    ()]);
    0.68
    VersionUID
    0.67
    Activations Density 22.012%

    No Known Activations