© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12878
    Prev
    Next
    INDEX
    Explanations

    time notations

    oai_token-act-pair · gemini-2.0-flash

    pm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    pm
    -1.69
     pm
    -1.52
    PM
    -1.45
     PM
    -1.44
    Pm
    -1.05
     Pm
    -1.00
    pms
    -0.76
    AccessorTable
    -0.71
    pmc
    -0.68
    ±
    -0.65
    POSITIVE LOGITS
    KEYCODE
    0.55
    Население
    0.55
     />\
    0.53
    帖最后由
    0.53
    InSection
    0.53
    lwjgl
    0.52
    complexType
    0.51
    atguigu
    0.51
    spira
    0.51
     actionMode
    0.49
    Activations Density 1.923%

    No Known Activations