© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6387
    Prev
    Next
    INDEX
    Explanations

    a mixture of conversational phrases in Malay and English

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    harusnya
    -0.65
    nodoc
    -0.58
     مرئيه
    -0.56
    GeoNames
    -0.52
    ValueStyle
    -0.49
    cedent
    -0.49
    ManagedBean
    -0.48
    KURZBESCHREIBUNG
    -0.46
    PYX
    -0.45
    .*")]
    -0.45
    POSITIVE LOGITS
    CppMethod
    0.54
    bastien
    0.54
    ratislava
    0.53
    enumi
    0.52
    Diweddarwch
    0.51
    +#+
    0.51
    boxylic
    0.50
    UVWXYZ
    0.49
     jí
    0.49
     Nan
    0.49
    Activations Density 0.428%

    No Known Activations