© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12064
    Prev
    Next
    INDEX
    Explanations

    common english words and sentence structure

    oai_token-act-pair · gemini-2.0-flash

    random document snippets

    np_max-act-logits · gemini-2.0-flash

    say "space" words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     purpoſe
    -0.76
     iconFacebook
    -0.74
    BibitemShut
    -0.74
    eſt
    -0.73
     Eſ
    -0.72
     Monfieur
    -0.72
    ſhip
    -0.71
     eſt
    -0.70
     iſt
    -0.69
    bibfield
    -0.69
    POSITIVE LOGITS
     AFS
    0.48
     FEC
    0.47
     OCS
    0.47
     PDC
    0.46
     FRP
    0.46
     BBS
    0.45
     EEU
    0.45
     oracles
    0.45
     Deity
    0.44
     CCM
    0.44
    Activations Density 48.930%

    No Known Activations