© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3858
    Prev
    Next
    INDEX
    Explanations

    various kinds of computer code related to memory and message management

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Whig
    -0.84
     NIST
    -0.78
     homoto
    -0.77
     LDA
    -0.77
     ſche
    -0.77
     auffi
    -0.75
     fevere
    -0.74
     WPS
    -0.73
     HMM
    -0.73
     MIPS
    -0.73
    POSITIVE LOGITS
     Br
    0.75
    ValueStyle
    0.74
     kasarigan
    0.74
     re
    0.73
     St
    0.72
     di
    0.70
     ad
    0.70
     ex
    0.69
     st
    0.69
     com
    0.68
    Activations Density 12.825%

    No Known Activations