© 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. 14838
    Prev
    Next
    INDEX
    Explanations

    the word "input" and words related to computer code or commands, particularly when discussing file types

    oai_token-act-pair · gemini-2.0-flash

    say "type" words

    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
     Type
    -2.69
     type
    -2.61
     types
    -2.56
     TYPE
    -2.55
    Type
    -2.38
    TYPE
    -2.34
     Types
    -2.34
    type
    -2.31
    types
    -2.28
     tipo
    -2.28
    POSITIVE LOGITS
    RegistryLite
    0.69
     pinulongan
    0.68
     heapq
    0.55
    AccessorTable
    0.55
     مرئيه
    0.48
    ⓧ
    0.48
    alnız
    0.47
    BindingResult
    0.47
    setViewportView
    0.46
     <=",
    0.44
    Activations Density 2.752%

    No Known Activations