© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5010
    Prev
    Next
    INDEX
    Explanations

    location/place names, team names and references to sporting events

    oai_token-act-pair · gemini-2.0-flash

    location and organization names

    np_max-act-logits · gemini-2.0-flash
    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
     sclerosis
    -0.66
     purpoſe
    -0.60
    Demografia
    -0.60
     bağlantılar
    -0.58
    ();)
    -0.57
     FishBase
    -0.56
     Escolar
    -0.56
    SequentialGroup
    -0.56
     tvb
    -0.55
     Père
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.72
    ngdoc
    0.55
    rungsseite
    0.54
     Zjednoc
    0.53
     Imp
    0.48
     toneladas
    0.47
    Exp
    0.46
    Imp
    0.44
    ########.
    0.44
    \{\\
    0.43
    Activations Density 0.389%

    No Known Activations