© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    code blocks that mention names

    oai_token-act-pair · gemini-2.0-flash

    name

    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
     autorytatywna
    -1.06
    ########.
    -1.01
     &___
    -0.84
    ponses
    -0.77
    rungsseite
    -0.74
    RTSC
    -0.69
     */;
    -0.69
    iastical
    -0.68
     själva
    -0.68
    Toponymie
    -0.66
    POSITIVE LOGITS
    OGND
    0.58
     SqlDbType
    0.50
     chromatin
    0.48
    Fprintf
    0.45
    globin
    0.44
    MathML
    0.42
     Gettysburg
    0.42
    fromCharCode
    0.42
    writerow
    0.42
    enterOuterAlt
    0.41
    Activations Density 0.199%

    No Known Activations