© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10591
    Prev
    Next
    INDEX
    Explanations

    various components of computer code.

    oai_token-act-pair · gemini-2.0-flash

    code and paths

    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
     raiſ
    -0.63
     Diſ
    -0.60
     pleaſure
    -0.59
     Majefty
    -0.57
     Conſ
    -0.56
     Monfieur
    -0.56
     poffe
    -0.56
     Reſ
    -0.56
     ſever
    -0.55
     ſtate
    -0.54
    POSITIVE LOGITS
    <bos>
    0.41
    rophoresis
    0.22
     și
    0.21
    ropathy
    0.20
    fecture
    0.19
    itively
    0.19
    ulitis
    0.19
    tabolism
    0.18
    sistor
    0.18
     así
    0.18
    Activations Density 0.353%

    No Known Activations