© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5207
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words 'no', 'other', 'matter' or 'and'

    oai_token-act-pair · gemini-2.0-flash

    no matter

    np_max-act · gemini-2.0-flash
    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
     labour
    -0.66
     specialise
    -0.63
     mano
    -0.62
     ‘
    -0.59
    labour
    -0.59
     https
    -0.58
    ,
    -0.57
     M
    -0.56
     http
    -0.56
     idea
    -0.52
    POSITIVE LOGITS
     Efq
    1.22
     purpoſe
    1.16
     ſmall
    1.14
    ſelf
    1.13
     raiſ
    1.13
     Majefty
    1.09
     ſtate
    1.08
     faſt
    1.07
     Anſ
    1.06
     Reſ
    1.05
    Activations Density 3.484%

    No Known Activations