© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11637
    Prev
    Next
    INDEX
    Explanations

    code blocks, especially related to JSON objects, API keys and error messages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    libft
    -0.70
    참고
    -0.65
    HasAnnotation
    -0.64
    featureID
    -0.63
     defaultstate
    -0.62
    quiel
    -0.61
     ivelany
    -0.60
    তথ্যসূত্র
    -0.59
     considérons
    -0.59
    AccessorTable
    -0.58
    POSITIVE LOGITS
     poffe
    0.48
     dieu
    0.43
     fhew
    0.42
     poffible
    0.42
     Partagez
    0.42
     ſtand
    0.42
    omock
    0.41
     makeStyles
    0.41
     LIRE
    0.40
     BorderRadius
    0.40
    Activations Density 1.746%

    No Known Activations