© 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. 9162
    Prev
    Next
    INDEX
    Explanations

    language describing technical or mechanical problems and fixes

    oai_token-act-pair · gemini-2.0-flash

    say "problem"

    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
     problems
    -2.53
    Problems
    -2.48
     Problems
    -2.47
    problems
    -2.44
    problem
    -2.42
    Problem
    -2.42
     Problem
    -2.41
     problem
    -2.39
     trouble
    -2.27
     PROBLEM
    -2.20
    POSITIVE LOGITS
    ThroughAttribute
    0.62
     تضيفلها
    0.60
    Einzelnachweise
    0.59
    Voci
    0.58
    ьаж
    0.54
     configureStore
    0.53
    amaño
    0.53
    CPtr
    0.52
    Cursors
    0.52
    RequestBuilder
    0.51
    Activations Density 2.994%

    No Known Activations