© 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. 8988
    Prev
    Next
    INDEX
    Explanations

    capitalized words or acronyms, especially when associated with titles or descriptors.

    oai_token-act-pair · gemini-2.0-flash

    roles and job titles

    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
     baseman
    -0.56
    createClass
    -0.56
     musician
    -0.49
     researcher
    -0.48
     guitarist
    -0.48
    Portály
    -0.46
     cubs
    -0.46
     biologist
    -0.46
    othed
    -0.45
     youtuber
    -0.44
    POSITIVE LOGITS
     Man
    0.86
     Student
    0.75
    StoryboardSegue
    0.74
    Man
    0.73
    User
    0.72
     Player
    0.72
     Perfon
    0.68
     Caller
    0.66
    Student
    0.65
    OrNil
    0.63
    Activations Density 8.484%

    No Known Activations