© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3214
    Prev
    Next
    INDEX
    Explanations

    references to the month of December

    oai_token-act-pair · gemini-2.0-flash

    December

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ObjectModel
    -0.42
    CDCl
    -0.42
    bootstrapcdn
    -0.42
     miesto
    -0.41
    ulipas
    -0.41
    गु
    -0.40
     Willard
    -0.40
    ῶν
    -0.40
     Профиль
    -0.40
     בני
    -0.40
    POSITIVE LOGITS
     OFDb
    0.78
     كومونز
    0.72
     GenerationType
    0.71
    tagHelperRunner
    0.71
    WriteTagHelper
    0.70
     noqa
    0.69
    AddTagHelper
    0.69
    EndGlobalSection
    0.68
    Personensuche
    0.68
    ConstraintMaker
    0.67
    Activations Density 1.067%

    No Known Activations