© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5286
    Prev
    Next
    INDEX
    Explanations

    descriptions of objects

    oai_token-act-pair · gemini-2.0-flash

    describing everyday objects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    таратура
    -0.72
     nahilalakip
    -0.58
    مصادر
    -0.56
    rungsseite
    -0.53
    scriptId
    -0.52
    󠁿
    -0.52
    Portail
    -0.52
    ValueStyle
    -0.51
     sticks
    -0.50
     {?>
    -0.50
    POSITIVE LOGITS
    bootstrapcdn
    0.65
    AutoScale
    0.60
    ResumeLayout
    0.58
     poffe
    0.57
     klachten
    0.57
    altezza
    0.55
    PrototypeOf
    0.53
    Validators
    0.52
     raiſ
    0.52
    ſelf
    0.51
    Activations Density 3.411%

    No Known Activations