© 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. 9170
    Prev
    Next
    INDEX
    Explanations

    lists of activities and items that one likes

    oai_token-act-pair · gemini-2.0-flash

    and or comma

    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
     persino
    -0.79
     addirittura
    -0.70
     enfans
    -0.68
     quelquefois
    -0.67
     eût
    -0.65
     siquiera
    -0.64
     nemlig
    -0.64
     gärna
    -0.63
     malah
    -0.62
     textStatus
    -0.60
    POSITIVE LOGITS
     of
    0.90
     ByteBuffer
    0.52
     solem
    0.51
    of
    0.50
    JFrame
    0.49
    Становништво
    0.49
    valents
    0.48
     balanceOf
    0.47
     incense
    0.47
    كويكب
    0.47
    Activations Density 8.599%

    No Known Activations