© 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. 6468
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and conversational language.

    oai_token-act-pair · gemini-2.0-flash

    but

    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
     itſelf
    -0.78
     Reſ
    -0.78
     незавершена
    -0.76
    +#+#
    -0.75
     Monfieur
    -0.74
     Efq
    -0.73
    ſelves
    -0.71
     Houſe
    -0.71
     ་་
    -0.70
     Majefty
    -0.70
    POSITIVE LOGITS
     Ka
    0.54
     Ar
    0.53
     Mar
    0.52
     La
    0.50
     J
    0.50
     az
    0.50
     National
    0.49
     luz
    0.49
     Se
    0.48
     College
    0.48
    Activations Density 12.562%

    No Known Activations