© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11982
    Prev
    Next
    INDEX
    Explanations

    family relationships or relationships to a higher power

    oai_token-act-pair · gemini-2.0-flash

    family members

    np_max-act-logits · 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
     poži
    -0.45
     dissociation
    -0.44
     HÀ
    -0.43
    UCTION
    -0.41
    KURZBESCHREIBUNG
    -0.40
     offenders
    -0.40
    EROS
    -0.40
    uktion
    -0.40
     phép
    -0.39
    udis
    -0.39
    POSITIVE LOGITS
    mappedBy
    0.70
    Izvori
    0.67
    LabelTagHelper
    0.66
     poveznice
    0.64
    StructEnd
    0.62
     bpy
    0.62
    脚注の使い方
    0.61
    WithIOException
    0.61
    mybatisplus
    0.60
    MENAFN
    0.60
    Activations Density 2.402%

    No Known Activations