© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8234
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers used in programming

    oai_token-act-pair · gemini-2.0-flash

    Code/hex representations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IsContent
    -0.75
     pm
    -0.69
    pm
    -0.69
    efd
    -0.68
     SIE
    -0.67
     PM
    -0.66
    fm
    -0.66
    sv
    -0.66
    LookAnd
    -0.66
    cd
    -0.65
    POSITIVE LOGITS
     }^{(
    0.50
     }}^{\
    0.46
    XmlAccessType
    0.44
    ]_{\
    0.43
    ]_{
    0.42
     ]
    0.42
     }_{
    0.41
     }}^{
    0.41
    l
    0.40
     }}(
    0.40
    Activations Density 10.144%

    No Known Activations