© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15600
    Prev
    Next
    INDEX
    Explanations

    what appears to be citations or references

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    intios
    -0.67
     consultato
    -0.64
    帖最后由
    -0.55
     חיצוניים
    -0.51
    consulté
    -0.51
    RenderAtEndOf
    -0.50
     ProtoMessage
    -0.50
    Referencies
    -0.49
    GEBURTSDATUM
    -0.49
     protoimpl
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.57
     born
    0.55
     borne
    0.53
    born
    0.52
    GraphicsUnit
    0.51
    brtc
    0.50
     createSlice
    0.49
    shocked
    0.49
    IAI
    0.49
     patches
    0.49
    Activations Density 8.126%

    No Known Activations