© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8766
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C++ and Java, but also JavaScript and possibly mathematical languages

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
     devenus
    -0.85
     nemlig
    -0.85
     soldati
    -0.84
     spørs
    -0.84
     móds
    -0.83
    ’,
    -0.83
     cioè
    -0.82
    ‘
    -0.82
     ufficio
    -0.82
    .’
    -0.81
    POSITIVE LOGITS
     للمعارف
    0.41
     يتيمه
    0.35
    AndEndTag
    0.29
     InputDecoration
    0.28
    OGND
    0.27
    Hochspringen
    0.26
     "..\..\..\
    0.26
    RenderAtEndOf
    0.25
     BoxDecoration
    0.25
     uParam
    0.25
    Activations Density 34.291%

    No Known Activations