© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15454
    Prev
    Next
    INDEX
    Explanations

    date ranges

    oai_token-act-pair · gemini-2.0-flash

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RTEX
    -0.94
     للاسماء
    -0.86
    новништво
    -0.86
    HomeAsUpEnabled
    -0.85
    GraphicsUnit
    -0.85
     Normdatei
    -0.82
     CreateTagHelper
    -0.81
    OGND
    -0.79
    SOUNDBITE
    -0.77
     ErrIntOverflow
    -0.77
    POSITIVE LOGITS
     quoi
    0.40
    1
    0.40
    2
    0.37
    e
    0.35
     entanto
    0.34
    atschappij
    0.34
    叶子
    0.34
    4
    0.34
    whatever
    0.33
     це
    0.33
    Activations Density 5.584%

    No Known Activations