© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11594
    Prev
    Next
    INDEX
    Explanations

    phrases related to steps in a scientific or mathematical process, especially how one thing leads to or is obtained from another

    oai_token-act-pair · gemini-2.0-flash

    obtained by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -0.83
     Monfieur
    -0.82
     quæ
    -0.73
     Cæsar
    -0.73
     varandra
    -0.73
     Efq
    -0.72
     Reſ
    -0.71
     enfans
    -0.69
     insuffisamment
    -0.68
     Référence
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.57
    (©
    0.48
     base
    0.47
     est
    0.46
    djangoproject
    0.45
    }}}$
    0.45
     imp
    0.44
    Portale
    0.44
     E
    0.44
    })}$
    0.44
    Activations Density 2.640%

    No Known Activations