© 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. 8237
    Prev
    Next
    INDEX
    Explanations

    sentences describing the method to do some scientific laboratory procedure.

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
    SharedDtor
    -0.65
    EnumMember
    -0.59
    ReusableCell
    -0.54
    ApiModelProperty
    -0.54
     Eisen
    -0.53
    dafx
    -0.52
    MergeFrom
    -0.51
     mergeFrom
    -0.50
    
    -0.50
     ExecuteAsync
    -0.49
    POSITIVE LOGITS
     समीक्षक
    0.82
     présidenti
    0.68
     set
    0.63
     sentarse
    0.58
     nationaux
    0.58
     ContentValues
    0.58
     étrangère
    0.57
     Set
    0.57
     وتسجيلات
    0.56
     صوتيه
    0.56
    Activations Density 2.551%

    No Known Activations