© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2011
    Prev
    Next
    INDEX
    Explanations

    various prepositions and certain capitalized words

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and data structure terms

    np_token-act-pair-logits · gpt-4o-mini

    European places and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GIVEREF
    -0.57
     Roskov
    -0.45
     CURLOPT
    -0.44
     jw
    -0.44
     EE
    -0.43
    َا
    -0.43
    okhttp
    -0.41
     Lauderdale
    -0.41
    řeba
    -0.41
     reserves
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.79
    GraphicsUnit
    0.79
    PageRoute
    0.73
    ItemBackground
    0.70
    afficheront
    0.63
    RetentionPolicy
    0.61
    routeProvider
    0.60
    OutputPath
    0.60
     MainAxisSize
    0.59
     spagno
    0.57
    Activations Density 0.187%

    No Known Activations