© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6008
    Prev
    Next
    INDEX
    Explanations

    the word "photos" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    photos

    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
    er
    -0.62
    س
    -0.56
    or
    -0.55
    Photo
    -0.54
    more
    -0.54
    ly
    -0.54
    photo
    -0.54
    Res
    -0.54
    i
    -0.54
    son
    -0.53
    POSITIVE LOGITS
    principalTable
    1.00
    NOPQRST
    0.96
     propOrder
    0.90
    !*\
    0.88
    pholes
    0.86
     Roskov
    0.82
    RenderAtEndOf
    0.80
     AssemblyTitle
    0.80
    Välislingid
    0.80
     tdci
    0.79
    Activations Density 1.046%

    No Known Activations