© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 7805
    Prev
    Next
    INDEX
    Explanations

    a combination of phrases describing a negative event experienced and phrases connected to doing something.

    oai_token-act-pair · gemini-2.0-flash

    The rest

    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
     remaining
    -2.97
     Remaining
    -2.86
    remaining
    -2.70
     rest
    -2.69
     remainder
    -2.56
    Remaining
    -2.56
    Rest
    -2.25
     Rest
    -2.20
    rest
    -2.16
     reste
    -2.06
    POSITIVE LOGITS
    曖昧さ回避
    0.45
    MethodImpl
    0.44
     دیکھیے
    0.43
    Билгалдахарш
    0.41
     siyang
    0.41
    حوالہ
    0.39
    ecore
    0.38
    ensatz
    0.37
    ChildScrollView
    0.37
    eniging
    0.37
    Activations Density 3.230%

    No Known Activations