© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11628
    Prev
    Next
    INDEX
    Explanations

    verbs conjugated in the past tense used to describe an outcome

    oai_token-act-pair · gemini-2.0-flash

    destruction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     незавершена
    -0.76
    Архівовано
    -0.63
    LookAnd
    -0.62
    TagMode
    -0.59
    الإنجليزية
    -0.54
     sahiptir
    -0.54
     UIFont
    -0.51
     buono
    -0.50
     enged
    -0.49
    urato
    -0.48
    POSITIVE LOGITS
     demolished
    0.96
     demolish
    0.90
     pulver
    0.88
     obliterated
    0.86
     obliter
    0.84
     annihil
    0.84
     demolition
    0.83
     decim
    0.82
     annihilated
    0.81
     tras
    0.81
    Activations Density 1.644%

    No Known Activations