© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12758
    Prev
    Next
    INDEX
    Explanations

    language related to a company or individual either ending employment or having their actions investigated

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_token-act-pair-logits · gpt-4o-mini

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ModelExpression
    -0.69
    ).}
    -0.68
    '},
    -0.68
    ).)
    -0.64
    .")]
    -0.58
    ).
    -0.57
    '],
    -0.56
    .}}
    -0.56
    "},
    -0.56
    ).]
    -0.55
    POSITIVE LOGITS
     "
    1.43
     “
    1.19
     „
    1.14
     ”
    1.07
     «
    1.05
    「
    1.02
     ''
    0.95
    "
    0.93
     "[
    0.88
     @"
    0.87
    Activations Density 11.800%

    No Known Activations