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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7140
    Prev
    Next
    INDEX
    Explanations

    the word "classic"

    oai_token-act-pair · gemini-2.0-flash

    classic

    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
    h
    -0.69
    m
    -0.68
    or
    -0.66
    l
    -0.65
    g
    -0.65
    x
    -0.64
    b
    -0.64
    I
    -0.63
    u
    -0.63
    ly
    -0.61
    POSITIVE LOGITS
    脚注の使い方
    1.28
    awtextra
    1.15
    }*/
    
    1.11
    "):
    
    1.09
    }`).
    1.06
    findpost
    1.01
    '):
    
    0.99
     >=",
    0.98
    BeginContext
    0.98
    ]:
    
    0.97
    Activations Density 4.688%

    No Known Activations