© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12926
    Prev
    Next
    INDEX
    Explanations

    code snippets and system information structures

    oai_token-act-pair · gemini-2.0-flash

    cg opt information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    sizeCache
    -0.91
    +#+#
    -0.85
    OGND
    -0.84
    脚注の使い方
    -0.82
    __':
    -0.82
    Зноскі
    -0.79
    findpost
    -0.77
    oa̍t
    -0.75
    #
    -0.74
    __':
    -0.74
    POSITIVE LOGITS
     vair
    0.42
     AttributeSet
    0.42
    ایا
    0.36
     basses
    0.34
    寒
    0.34
    VSS
    0.33
    aruhi
    0.33
     surfaces
    0.33
    <!--
    0.32
     herring
    0.32
    Activations Density 4.853%

    No Known Activations