© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13871
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters fighting or being defeated

    oai_token-act-pair · gemini-2.0-flash

    Vo or Answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
      
    -0.53
    .
    -0.45
     forKey
    -0.45
     واس
    -0.44
    )
    -0.44
     ri
    -0.44
    sip
    -0.43
    ரிய
    -0.43
     Lic
    -0.43
    метр
    -0.43
    POSITIVE LOGITS
     Majefty
    1.02
     purpoſe
    1.01
     myſelf
    0.99
     poffe
    0.95
     pleaſure
    0.94
     itſelf
    0.91
     fubject
    0.89
     iſt
    0.87
     Efq
    0.85
     ſtate
    0.84
    Activations Density 1.633%

    No Known Activations