© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5333
    Prev
    Next
    INDEX
    Explanations

    phrases that appear to be conclusions or summaries of facts

    oai_token-act-pair · gemini-2.0-flash

    confirmation, evidence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    RegistryLite
    -0.70
     Efq
    -0.69
    openzeppelin
    -0.68
    SharedDtor
    -0.67
     iſt
    -0.67
    yargs
    -0.67
     poffible
    -0.66
     houſe
    -0.65
    Бахар
    -0.65
     كومونز
    -0.64
    POSITIVE LOGITS
     proves
    0.77
     indicates
    0.75
     evidence
    0.68
     confirms
    0.68
     demonstrates
    0.65
     Indicates
    0.65
     proof
    0.63
     indicate
    0.63
     prove
    0.63
     confirm
    0.60
    Activations Density 3.047%

    No Known Activations