© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words that are applicable to many contexts, as if choosing words at random

    oai_token-act-pair · gemini-2.0-flash

    various services/industries

    np_max-act-logits · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Efq
    -0.90
     تضيفلها
    -0.85
    UnusedPrivate
    -0.80
     GenerationType
    -0.79
     arşivlendi
    -0.76
    awtextra
    -0.71
     gynhyrchwyd
    -0.68
    WithIOException
    -0.68
     Anſ
    -0.68
     defaultstate
    -0.67
    POSITIVE LOGITS
     the
    0.68
    onomies
    0.55
    oner
    0.53
     It
    0.51
    richTextPanel
    0.50
     John
    0.49
    ly
    0.49
     
    0.49
     Kenyatta
    0.47
     it
    0.46
    Activations Density 12.618%

    No Known Activations