© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3804
    Prev
    Next
    INDEX
    Explanations

    sentences where the author admits bias or expresses an opinion in research contexts

    oai_token-act-pair · gemini-2.0-flash

    bias

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     vanligt
    -0.46
     desafi
    -0.43
     hidrá
    -0.43
    Спољашње
    -0.41
    MULTIP
    -0.40
     Milli
    -0.40
     słow
    -0.39
    xcd
    -0.39
    })();
    -0.39
    ætter
    -0.39
    POSITIVE LOGITS
     bias
    1.56
     biased
    1.50
    biased
    1.31
     biases
    1.30
     Bias
    1.28
    bias
    1.25
    biases
    1.16
    Bias
    1.13
    BIAS
    1.09
     prejudiced
    1.02
    Activations Density 3.175%

    No Known Activations