© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10238
    Prev
    Next
    INDEX
    Explanations

    code snippets from a variety of computer languages

    oai_token-act-pair · gemini-2.0-flash

    declarations of integer types

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

    int or integer

    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
     numbers
    -0.52
    numbers
    -0.51
     Numbers
    -0.44
    τεύ
    -0.44
     Reale
    -0.43
     Number
    -0.43
    Number
    -0.43
     real
    -0.42
     reale
    -0.40
     Repetition
    -0.40
    POSITIVE LOGITS
     int
    1.73
    int
    1.53
     Int
    1.49
    Int
    1.36
     INT
    1.33
    INT
    1.18
     integer
    1.09
     ints
    1.05
     Integer
    1.05
    Integer
    1.02
    Activations Density 1.966%

    No Known Activations