© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of potentially negative terms, with no clear unifying theme

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     —
    -1.78
    —
    -1.63
     –
    -1.51
     --
    -1.48
    ——
    -1.30
    — 
    -1.29
     ——
    -1.23
     ―
    -1.18
    ―
    -1.13
     −
    -1.12
    POSITIVE LOGITS
    /+
    0.55
    റ്
    0.45
     ↑
    0.45
    (+)
    0.41
    /=
    0.41
    不肯
    0.41
    COA
    0.40
    шению
    0.40
    ย์
    0.39
    说不
    0.39
    Activations Density 1.239%

    No Known Activations