Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7616
    Prev
    Next
    INDEX
    Explanations

    the word "vision" and related terms like "visionary"

    oai_token-act-pair · gemini-2.0-flash

    vision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -2.09
     itſelf
    -1.91
     pleaſure
    -1.80
     becauſe
    -1.80
     themſelves
    -1.77
     himſelf
    -1.77
     Efq
    -1.71
     Monfieur
    -1.70
     Theſe
    -1.65
     Jefus
    -1.63
    POSITIVE LOGITS
     den
    0.84
     mit
    0.83
     la
    0.82
     n
    0.80
     der
    0.79
     le
    0.76
     de
    0.75
     z
    0.74
     les
    0.73
     m
    0.71
    Activations Density 3.228%

    No Known Activations