© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    the word "am" and sometimes other words that look like it such as "acid" or "he"

    oai_token-act-pair · gemini-2.0-flash

    am

    np_max-act · gemini-2.0-flash

    am

    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
     am
    -0.94
     Am
    -0.88
     P
    -0.82
     
    -0.79
     I
    -0.79
     a
    -0.77
     the
    -0.76
     “
    -0.76
     A
    -0.73
     an
    -0.73
    POSITIVE LOGITS
     Efq
    1.50
     pleaſure
    1.34
    Personensuche
    1.34
     Monfieur
    1.32
     Majefty
    1.31
     beginnetje
    1.29
     houſe
    1.28
    WithIOException
    1.26
    LookAnd
    1.25
     Jefus
    1.23
    Activations Density 1.404%

    No Known Activations