© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or people involved in a conversation.

    oai_token-act-pair · gemini-2.0-flash

    certainty

    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
    MigrationBuilder
    -0.78
    ScopeManager
    -0.75
    uminense
    -0.72
     ProtoMessage
    -0.71
     فريبيس
    -0.69
    enumi
    -0.67
    Билгалдахарш
    -0.66
     ujednoznacz
    -0.64
    MLLoader
    -0.61
     gynhyrchwyd
    -0.61
    POSITIVE LOGITS
     sure
    3.33
    sure
    2.45
    Sure
    2.33
     Sure
    2.30
     SURE
    2.19
     sûr
    1.33
     certain
    1.23
     CERTAIN
    1.06
     Certain
    1.05
    certain
    1.05
    Activations Density 2.532%

    No Known Activations