© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    words related to corporate meetings and processes, and words with "educat"

    oai_token-act-pair · gemini-2.0-flash

    educational events and resources

    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
     Workshop
    -0.75
     workshop
    -0.74
     Workshops
    -0.68
    workshop
    -0.67
     WORKSHOP
    -0.66
    Workshops
    -0.64
    Workshop
    -0.63
     seminar
    -0.59
     workshops
    -0.58
     Tour
    -0.53
    POSITIVE LOGITS
     protoimpl
    0.66
    oredCriteria
    0.54
     अनुसार
    0.50
    imread
    0.49
     caufe
    0.48
    ficulty
    0.47
     entidad
    0.47
    Jîn
    0.47
    inobu
    0.46
    듯
    0.45
    Activations Density 3.235%

    No Known Activations