© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    frequent function words and other words used to link parts of sentences (not, that, with, but, about)

    oai_token-act-pair · gemini-2.0-flash

    Text processing/writing

    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
     It
    -1.63
    It
    -1.21
     They
    -1.17
    They
    -0.97
     Its
    -0.84
    Its
    -0.81
     Оно
    -0.78
     Она
    -0.77
     它
    -0.75
     Mereka
    -0.71
    POSITIVE LOGITS
     is
    0.71
     onCreateView
    0.53
     /\.(
    0.50
    !*\
    0.49
    apunov
    0.49
     IS
    0.49
     numerus
    0.47
    GEBURTSDATUM
    0.46
    >>;
    0.45
    자인
    0.44
    Activations Density 14.646%

    No Known Activations