© 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. 13090
    Prev
    Next
    INDEX
    Explanations

    the prefix "tri"

    oai_token-act-pair · gemini-2.0-flash

    tri

    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
    </em>
    -0.85
     
    -0.81
     “
    -0.77
     Ro
    -0.73
    </strong>
    -0.69
     or
    -0.68
     K
    -0.66
     R
    -0.66
     I
    -0.66
     Re
    -0.65
    POSITIVE LOGITS
     myſelf
    2.06
     raiſ
    1.91
     Monfieur
    1.90
     ſever
    1.89
     Efq
    1.88
     Jefus
    1.82
     pleaſure
    1.81
     Anſ
    1.77
     purpoſe
    1.77
     whoſe
    1.68
    Activations Density 1.140%

    No Known Activations