© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13108
    Prev
    Next
    INDEX
    Explanations

    the word "voice" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    voice

    np_max-act · gemini-2.0-flash

    voice

    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
      
    -1.03
    1
    -0.99
        
    -0.98
    0
    -0.95
       
    -0.95
    ta
    -0.93
    2
    -0.86
             
    -0.84
            
    -0.83
    ma
    -0.83
    POSITIVE LOGITS
     itſelf
    1.37
     myſelf
    1.36
     $_"
    1.36
     Efq
    1.34
     Houſe
    1.33
    "]);
    1.30
    ^(@)
    1.30
     raiſ
    1.29
     Reſ
    1.29
    ſelves
    1.27
    Activations Density 3.140%

    No Known Activations