© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7457
    Prev
    Next
    INDEX
    Explanations

    US place names, especially of Nebraska, and references.

    oai_token-act-pair · gemini-2.0-flash

    Nebraska and Omaha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    UserScript
    -0.53
     Roskov
    -0.52
    ServletException
    -0.50
    HideFlags
    -0.50
    wet
    -0.49
    ρύ
    -0.49
     Biosciences
    -0.46
    shi
    -0.46
    celtic
    -0.44
    aacute
    -0.44
    POSITIVE LOGITS
    μως
    0.60
     resourceCulture
    0.60
    +#+
    0.60
    EDEFAULT
    0.59
    LabelTagHelper
    0.58
    OpenHelper
    0.56
     चीज़ों
    0.56
     continúas
    0.55
    djangoproject
    0.54
     صوتيه
    0.52
    Activations Density 6.676%

    No Known Activations