© 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. 12494
    Prev
    Next
    INDEX
    Explanations

    the word "sad", and sometimes words related to negativity

    oai_token-act-pair · gemini-2.0-flash

    sad

    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
    ElementException
    -0.61
     her
    -0.60
    </b>
    -0.60
     []:
    -0.59
     et
    -0.57
     M
    -0.57
     V
    -0.55
    </h1>
    -0.55
    ­
    -0.54
     sad
    -0.54
    POSITIVE LOGITS
     myſelf
    1.30
    <bos>
    1.23
     Monfieur
    1.22
     itſelf
    1.19
     pleaſure
    1.16
     Shakspeare
    1.13
     fubject
    1.06
     themſelves
    1.05
     raiſ
    1.04
     Theſe
    1.04
    Activations Density 1.158%

    No Known Activations