© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7821
    Prev
    Next
    INDEX
    Explanations

    the word 'max', sometimes capitalized, often near related words such as 'min'

    oai_token-act-pair · gemini-2.0-flash

    Max

    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
    contentLoaded
    -0.72
     يتيمه
    -0.68
    RTGC
    -0.67
     OMIT
    -0.65
     unknownFields
    -0.65
    MLLoader
    -0.64
    ⓧ
    -0.64
    addGap
    -0.64
    WithIOException
    -0.64
    '),
    
    -0.63
    POSITIVE LOGITS
     pleaſure
    1.34
     houſe
    1.30
     purpoſe
    1.26
     myſelf
    1.23
     Monfieur
    1.23
     Shakspeare
    1.20
     Efq
    1.19
     ſtate
    1.15
     greateſt
    1.15
     ſche
    1.14
    Activations Density 1.461%

    No Known Activations