© 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. 10782
    Prev
    Next
    INDEX
    Explanations

    LaTeX code fragments

    oai_token-act-pair · gemini-2.0-flash

    }

    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
    setVerticalGroup
    -1.02
     فريبيس
    -0.90
    SharedDtor
    -0.89
    BASEPATH
    -0.84
    UnknownFieldSet
    -0.83
    AndEndTag
    -0.81
    UnknownFields
    -0.79
    nodoc
    -0.79
     "..\..\
    -0.77
     McDon
    -0.77
    POSITIVE LOGITS
    <bos>
    0.91
     the
    0.86
     a
    0.70
     and
    0.67
    </strong>
    0.66
    )
    0.66
    </b>
    0.64
     that
    0.60
     she
    0.59
    </h1>
    0.58
    Activations Density 0.463%

    No Known Activations