© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14130
    Prev
    Next
    INDEX
    Explanations

    many articles, prepositions, certain numbers, and words seemingly next to adjectives in some cases.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     AutoMapper
    -0.47
     viewDidLoad
    -0.45
    JsonIgnore
    -0.43
     XCTest
    -0.43
    cabe
    -0.42
    varargin
    -0.42
    流
    -0.42
     Grounds
    -0.41
    Particular
    -0.41
    Przypisy
    -0.41
    POSITIVE LOGITS
     most
    1.09
    most
    0.84
    Most
    0.79
     moft
    0.77
     moſt
    0.73
    MessageOf
    0.73
     MOST
    0.68
     Most
    0.68
     transfieras
    0.63
    MOST
    0.61
    Activations Density 0.879%

    No Known Activations