© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    words and punctuation frequently used in scientific research papers to describe methodology

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     оригіналу
    -0.68
    +#+#
    -0.59
     cropping
    -0.57
     ujednoznacz
    -0.57
    HasAnnotation
    -0.54
    cropping
    -0.54
    TypedDataSet
    -0.53
    ValueGeneration
    -0.50
    DebuggerNonUser
    -0.49
    appliquent
    -0.49
    POSITIVE LOGITS
     Reverso
    0.64
     }}"></
    0.56
     denn
    0.55
     defaultstate
    0.55
    idency
    0.54
    JsonProperty
    0.50
     Aires
    0.49
    verwijspagina
    0.48
    },[])
    0.48
     BoxFit
    0.47
    Activations Density 2.285%

    No Known Activations