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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those representing years or quantities, often with commas

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Personendaten
    -0.73
    tiness
    -0.72
    PyExc
    -0.71
    }}}
    -0.69
    GIH
    -0.66
    ^(@)
    -0.66
     /\.
    -0.65
    bedo
    -0.65
    ̍t
    -0.64
     Odo
    -0.64
    POSITIVE LOGITS
    ,
    0.96
     millions
    0.69
     thousands
    0.66
    thousands
    0.63
     millones
    0.59
     milhões
    0.59
     Thousands
    0.59
     Millions
    0.59
    millions
    0.58
    Millions
    0.55
    Activations Density 0.916%

    No Known Activations