© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16226
    Prev
    Next
    INDEX
    Explanations

    snippets of program source code mixed with natural language

    oai_token-act-pair · gemini-2.0-flash

    portuguese or computer code

    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
     Theſe
    -1.02
     Cæsar
    -0.95
     Diſ
    -0.86
     Houſe
    -0.86
     Jefus
    -0.84
     Shaksp
    -0.84
     Shakspeare
    -0.84
     negroes
    -0.82
     unpublished
    -0.81
     Anſ
    -0.79
    POSITIVE LOGITS
     the
    0.74
     is
    0.69
     es
    0.63
    TagHelper
    0.60
     am
    0.59
     Es
    0.58
     an
    0.56
     esto
    0.56
    __))
    0.55
     ab
    0.54
    Activations Density 0.175%

    No Known Activations