© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4765
    Prev
    Next
    INDEX
    Explanations

    incomplete or negated thoughts that show a degree of conviction or certainty

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     percentage
    -0.96
     percent
    -0.92
    percent
    -0.88
     Percent
    -0.87
    Percent
    -0.84
     Percentage
    -0.84
     (%)
    -0.83
     %
    -0.82
    percentage
    -0.81
     percentages
    -0.77
    POSITIVE LOGITS
     Vikipedi
    0.65
    TargetException
    0.57
    >{@
    0.54
    iecie
    0.53
    }],
    0.51
    ########.
    0.50
     Walkover
    0.50
    verläs
    0.50
    SpringRunner
    0.49
    __:
    0.48
    Activations Density 0.357%

    No Known Activations