© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    the use of a speaking voice, including discussion of the quality or effectiveness of the voice and words like bonus

    oai_token-act-pair · 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
    <eos>
    -0.95
    -
    -0.86
     
    -0.84
    ,
    -0.84
     I
    -0.82
     Z
    -0.81
     “
    -0.80
     R
    -0.79
     -
    -0.78
     de
    -0.78
    POSITIVE LOGITS
     Efq
    2.34
     Jefus
    2.23
     myſelf
    2.22
    ſelf
    2.13
     purpoſe
    2.11
     Majefty
    2.09
     itſelf
    2.06
     Monfieur
    2.06
     houſe
    2.05
     themſelves
    2.03
    Activations Density 1.344%

    No Known Activations