© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7800
    Prev
    Next
    INDEX
    Explanations

    the word "cannot".

    oai_token-act-pair · gemini-2.0-flash

    cannot

    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
     cannot
    -1.68
    cannot
    -1.52
     myſelf
    -1.44
     Cannot
    -1.42
     Efq
    -1.39
     Majefty
    -1.28
     purpoſe
    -1.26
     CANNOT
    -1.21
     raiſ
    -1.20
     Jefus
    -1.20
    POSITIVE LOGITS
    t
    1.09
    ↵↵
    1.04
    ↵
    1.00
     not
    0.96
     Not
    0.89
    not
    0.88
    Not
    0.85
      
    0.81
     
    0.75
     NOT
    0.73
    Activations Density 2.057%

    No Known Activations