© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4097
    Prev
    Next
    INDEX
    Explanations

    the words "lose", "hit", and "DNA"

    oai_token-act-pair · gemini-2.0-flash

    lose/hit

    np_max-act · gemini-2.0-flash

    lose

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     surla
    -0.76
    .
    -0.60
    -
    -0.59
    Примечания
    -0.59
    (
    -0.58
    consulté
    -0.55
    ,
    -0.55
    :
    -0.54
    L
    -0.54
    |
    -0.54
    POSITIVE LOGITS
     itſelf
    1.18
     Majefty
    1.15
     myſelf
    1.14
     purpoſe
    1.13
     ſta
    1.09
     ſtate
    1.07
     ſche
    1.05
     themſelves
    1.04
     ſeveral
    1.02
     himſelf
    1.02
    Activations Density 1.737%

    No Known Activations