© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10686
    Prev
    Next
    INDEX
    Explanations

    general positive sentiment, particularly when combined with the words "much" or "way."

    oai_token-act-pair · gemini-2.0-flash

    Broad ranging discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Monfieur
    -0.90
    UrlResolution
    -0.90
     raiſ
    -0.88
     Eſ
    -0.85
    StreetMap
    -0.84
     ſeveral
    -0.82
     itſelf
    -0.82
     pleaſure
    -0.82
     Anſ
    -0.81
     Theſe
    -0.81
    POSITIVE LOGITS
     the
    1.00
    the
    0.74
     how
    0.43
    j
    0.42
    J
    0.40
    Referencies
    0.39
     صباح
    0.39
    any
    0.38
    лей
    0.38
    Бере
    0.38
    Activations Density 1.966%

    No Known Activations