© 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. 6627
    Prev
    Next
    INDEX
    Explanations

    parts of code in various programming languages (C++, Python, Javascript, etc.)

    oai_token-act-pair · gemini-2.0-flash

    coding/technical context

    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
     fubject
    -0.68
     Majefty
    -0.67
    Espèce
    -0.67
     neceff
    -0.66
     незавершена
    -0.63
    CompleteListener
    -0.63
     ſtill
    -0.63
    EDEFAULT
    -0.63
     Chriftian
    -0.61
     nakalista
    -0.61
    POSITIVE LOGITS
    ⓧ
    0.53
    кипедия
    0.52
    ResumeLayout
    0.47
    лото
    0.47
    ("")]
    0.47
     ProtoMessage
    0.46
    系列
    0.45
    yd
    0.45
    InitStruct
    0.45
    νη
    0.44
    Activations Density 2.950%

    No Known Activations