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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14575
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions related to actions involving scientific procedures

    oai_token-act-pair · gemini-2.0-flash

    flat surfaces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Theſe
    -0.94
     Efq
    -0.89
     Houſe
    -0.88
    WriteBarrier
    -0.87
     becauſe
    -0.86
    berdayakan
    -0.85
     فريبيس
    -0.84
     myſelf
    -0.84
     ―――――
    -0.84
     nahilalakip
    -0.82
    POSITIVE LOGITS
     plate
    0.85
     flat
    0.71
     plates
    0.69
     sheet
    0.67
    plate
    0.67
     surface
    0.66
     on
    0.66
     canvas
    0.65
     page
    0.64
    flat
    0.63
    Activations Density 3.745%

    No Known Activations