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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6381
    Prev
    Next
    INDEX
    Explanations

    negation words

    np_token-act-pair-logits · gpt-4o-mini

    uses of the words "to" and "no" or sentences including "it is"

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Monfieur
    -0.73
     myſelf
    -0.73
     Theſe
    -0.72
    +#+#
    -0.70
     itſelf
    -0.70
     themſelves
    -0.65
     متعلقه
    -0.65
     ſtate
    -0.65
     Reſ
    -0.64
    ingway
    -0.64
    POSITIVE LOGITS
     no
    3.05
    no
    2.30
    No
    1.84
     NO
    1.76
     No
    1.73
    NO
    1.57
     keine
    1.32
     kein
    1.32
     geen
    1.28
     нет
    1.24
    Activations Density 1.984%

    No Known Activations