© 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. 4182
    Prev
    Next
    INDEX
    Explanations

    a mix of possibly date-related words, math symbols and non-English words

    oai_token-act-pair · gemini-2.0-flash

    unusual language and characters

    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
     is
    -0.91
    IUrlHelper
    -0.76
     autorytatywna
    -0.70
    SourceChecksum
    -0.69
     can
    -0.69
     arrives
    -0.62
    rungsseite
    -0.59
     handleMessage
    -0.59
     awaits
    -0.59
     sits
    -0.59
    POSITIVE LOGITS
    __((
    0.52
    ільки
    0.48
     riesce
    0.47
     břez
    0.46
    drawable
    0.45
    InitStruct
    0.45
    mphony
    0.43
     funziona
    0.43
    mogat
    0.43
     dovrà
    0.42
    Activations Density 0.354%

    No Known Activations